# Nodebench MCP server

Agent View of the PolicyLayer registry record for Nodebench: identity, probed posture, risk grade, and all 824 tools classified. HTML page: https://policylayer.com/tools/io-github-homenshum-nodebench

## Facts

- Server id: `nodebench-mcp`
- Install: `npx -y nodebench-mcp`
- Homepage: https://github.com/HomenShum/nodebench-ai
- Registry record: grade F, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 824
- Tool categories present: Destructive, Execute, Read, Write
- Tags: io github homenshum nodebench, admin, automation
- Record last modified: 2026-06-28T16:09:08.254Z

## Tools (824)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `abandon_cycle` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/abandon-cycle.md |
| `archiveDocument` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/archivedocument.md |
| `cleanup_stale_runs` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/cleanup-stale-runs.md |
| `deeptrace_revoke_passport` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-revoke-passport.md |
| `delete_learning` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/delete-learning.md |
| `delete_sandbox_policy` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/delete-sandbox-policy.md |
| `deleteAgentMemory` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/deleteagentmemory.md |
| `removeDocumentFromFolder` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/removedocumentfromfolder.md |
| `share_revoke_packet_link` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/share-revoke-packet-link.md |
| `unload_toolset` | Destructive | Critical | https://policylayer.com/tools/io-github-homenshum-nodebench/unload-toolset.md |
| `benchmark_models` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/benchmark-models.md |
| `bootstrap_parallel_agents` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/bootstrap-parallel-agents.md |
| `build_banking_packet` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-banking-packet.md |
| `build_company_profile_starter` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-company-profile-starter.md |
| `build_founder_operating_model` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-founder-operating-model.md |
| `build_research_digest` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-research-digest.md |
| `build_shared_context_subscription` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-shared-context-subscription.md |
| `build_shared_context_subscription_manifest` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-shared-context-subscription-manifest.md |
| `build_submission_export` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-submission-export.md |
| `build_temporal_graph` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/build-temporal-graph.md |
| `burst_capture` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/burst-capture.md |
| `call_driver_tool` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/call-driver-tool.md |
| `call_llm` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/call-llm.md |
| `call_openclaw_skill` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/call-openclaw-skill.md |
| `call_webmcp_tool` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/call-webmcp-tool.md |
| `capture_surface_stats` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/capture-surface-stats.md |
| `capture_ui_screenshot` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/capture-ui-screenshot.md |
| `compile_decision_packet` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/compile-decision-packet.md |
| `compile_scenarios` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/compile-scenarios.md |
| `compile_tension_model` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/compile-tension-model.md |
| `compute_ssim_analysis` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/compute-ssim-analysis.md |
| `connect_mcp_driver` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/connect-mcp-driver.md |
| `connect_openclaw` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/connect-openclaw.md |
| `connect_webmcp_origin` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/connect-webmcp-origin.md |
| `convex_pre_deploy_gate` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-pre-deploy-gate.md |
| `convex_quality_gate` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-quality-gate.md |
| `delta_self_dogfood` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-self-dogfood.md |
| `disconnect_driver` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/disconnect-driver.md |
| `disconnect_openclaw` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/disconnect-openclaw.md |
| `disconnect_webmcp_origin` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/disconnect-webmcp-origin.md |
| `dive_auto_discover` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-auto-discover.md |
| `dive_fix_verify` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-fix-verify.md |
| `dive_interaction_test` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-interaction-test.md |
| `dive_reexplore` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-reexplore.md |
| `end_openclaw_session` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/end-openclaw-session.md |
| `enforce_merge_gate` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/enforce-merge-gate.md |
| `extract_video_frames` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-video-frames.md |
| `founder_local_weekly_reset` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-local-weekly-reset.md |
| `get_path_replay` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/get-path-replay.md |
| `gtm_script_builder` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/gtm-script-builder.md |
| `invoke_openclaw_skill` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/invoke-openclaw-skill.md |
| `invoke_view_tool` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/invoke-view-tool.md |
| `judge_request_retry` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/judge-request-retry.md |
| `judge_tool_output` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/judge-tool-output.md |
| `load_toolset` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/load-toolset.md |
| `log_interaction` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/log-interaction.md |
| `manipulate_screenshot` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/manipulate-screenshot.md |
| `navigate_to_view` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/navigate-to-view.md |
| `nb_start_agent` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-start-agent.md |
| `nb_switch_research_tab` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-switch-research-tab.md |
| `nodebench_ask_agent` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-ask-agent.md |
| `nodebench_navigate` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-navigate.md |
| `nodebench.claims.verify` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.claims.verify.md |
| `nodebench.research_role` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.research-role.md |
| `nodebench.research_run` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.research-run.md |
| `open_dive_dashboard` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/open-dive-dashboard.md |
| `open_local_dashboard` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/open-local-dashboard.md |
| `project_financials` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/project-financials.md |
| `readiness_scan` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/readiness-scan.md |
| `render_flow_visualization` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/render-flow-visualization.md |
| `request_execution_approval` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/request-execution-approval.md |
| `run_autonomous_loop` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-autonomous-loop.md |
| `run_benchmark_batch` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-benchmark-batch.md |
| `run_browserstack_benchmark_lane` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-browserstack-benchmark-lane.md |
| `run_closed_loop` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-closed-loop.md |
| `run_code_analysis` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-code-analysis.md |
| `run_competitor_signal_benchmark` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-competitor-signal-benchmark.md |
| `run_deep_sim` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-deep-sim.md |
| `run_dogfood_batch_with_judge` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-dogfood-batch-with-judge.md |
| `run_entity_intelligence_mission` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-entity-intelligence-mission.md |
| `run_flicker_detection` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-flicker-detection.md |
| `run_founder_autonomy_benchmark` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-founder-autonomy-benchmark.md |
| `run_graphify` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-graphify.md |
| `run_judge_loop` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-judge-loop.md |
| `run_mandatory_flywheel` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-mandatory-flywheel.md |
| `run_oracle_comparison` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-oracle-comparison.md |
| `run_packet_to_implementation_benchmark` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-packet-to-implementation-benchmark.md |
| `run_quality_gate` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-quality-gate.md |
| `run_recon` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-recon.md |
| `run_research_cell` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-research-cell.md |
| `run_self_directed_delivery_loop` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-self-directed-delivery-loop.md |
| `run_self_heal` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-self-heal.md |
| `run_self_maintenance` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-self-maintenance.md |
| `run_signal_sweep` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-signal-sweep.md |
| `run_sync_bridge_flush` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-sync-bridge-flush.md |
| `run_tests_cli` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-tests-cli.md |
| `run_visual_qa_suite` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/run-visual-qa-suite.md |
| `runNewsroomPipeline` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/runnewsroompipeline.md |
| `runSpotFixScan` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/runspotfixscan.md |
| `sandbox_batch` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/sandbox-batch.md |
| `sandbox_execute` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/sandbox-execute.md |
| `scrapling_crawl` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/scrapling-crawl.md |
| `scrapling_crawl_stop` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/scrapling-crawl-stop.md |
| `self_implement` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/self-implement.md |
| `simulate_decision_paths` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/simulate-decision-paths.md |
| `smart_select_tools` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/smart-select-tools.md |
| `spawn_openclaw_agent` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/spawn-openclaw-agent.md |
| `start_autonomy_benchmark` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/start-autonomy-benchmark.md |
| `start_dogfood_session` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/start-dogfood-session.md |
| `start_eval_run` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/start-eval-run.md |
| `start_execution_run` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/start-execution-run.md |
| `start_ui_dive` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/start-ui-dive.md |
| `start_verification_cycle` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/start-verification-cycle.md |
| `switchTab` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/switchtab.md |
| `thompson_pipeline` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/thompson-pipeline.md |
| `transcribe_audio_file` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/transcribe-audio-file.md |
| `trigger_batch_run` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/trigger-batch-run.md |
| `trigger_investigation` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/trigger-investigation.md |
| `triple_verify` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/triple-verify.md |
| `validate_agent_compatibility` | Execute | High | https://policylayer.com/tools/io-github-homenshum-nodebench/validate-agent-compatibility.md |
| `analyze_experiment_data` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/analyze-experiment-data.md |
| `analyze_figma_flows` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/analyze-figma-flows.md |
| `analyze_repo` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/analyze-repo.md |
| `analyze_screenshot` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/analyze-screenshot.md |
| `analyze_seo_content` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/analyze-seo-content.md |
| `analyze_voice_config` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/analyze-voice-config.md |
| `ask_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/ask-context.md |
| `assess_risk` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/assess-risk.md |
| `audit_openclaw_skills` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/audit-openclaw-skills.md |
| `audit_workflow_definition` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/audit-workflow-definition.md |
| `auditTelemetry` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/audittelemetry.md |
| `benchmark_voice_latency` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/benchmark-voice-latency.md |
| `build_claim_graph` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/build-claim-graph.md |
| `build_diligence_packet` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/build-diligence-packet.md |
| `build_investor_packet` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/build-investor-packet.md |
| `burn_rate_sanity` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/burn-rate-sanity.md |
| `calculate_terminal_value` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/calculate-terminal-value.md |
| `calculate_valuation` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/calculate-valuation.md |
| `calculate_wacc` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/calculate-wacc.md |
| `capture_responsive_suite` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/capture-responsive-suite.md |
| `cheapest_valid_path` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/cheapest-valid-path.md |
| `check_agent_inbox` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-agent-inbox.md |
| `check_contract_compliance` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-contract-compliance.md |
| `check_design_compliance` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-design-compliance.md |
| `check_dive_drivers` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-dive-drivers.md |
| `check_email_setup` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-email-setup.md |
| `check_framework_updates` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-framework-updates.md |
| `check_git_compliance` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-git-compliance.md |
| `check_mcp_setup` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-mcp-setup.md |
| `check_openclaw_setup` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-openclaw-setup.md |
| `check_openclaw_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-openclaw-status.md |
| `check_page_performance` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-page-performance.md |
| `check_paper_logic` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-paper-logic.md |
| `check_peer_messages` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-peer-messages.md |
| `check_plugin_update_readiness` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-plugin-update-readiness.md |
| `check_skill_freshness` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-skill-freshness.md |
| `check_webmcp_setup` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-webmcp-setup.md |
| `check_wordpress_site` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/check-wordpress-site.md |
| `claim_verification_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/claim-verification-scan.md |
| `classify_failure` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/classify-failure.md |
| `cluster_figma_flows` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/cluster-figma-flows.md |
| `compare` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compare.md |
| `compare_eval_runs` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compare-eval-runs.md |
| `compare_founder_directions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compare-founder-directions.md |
| `compare_options` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compare-options.md |
| `compare_savings` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compare-savings.md |
| `compare_workflow_paths` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compare-workflow-paths.md |
| `compute_calibration` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compute-calibration.md |
| `compute_web_stability` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/compute-web-stability.md |
| `connect_channels` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/connect-channels.md |
| `convex_analyze_components` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-analyze-components.md |
| `convex_analyze_http` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-analyze-http.md |
| `convex_audit_actions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-actions.md |
| `convex_audit_authorization` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-authorization.md |
| `convex_audit_data_modeling` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-data-modeling.md |
| `convex_audit_dev_setup` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-dev-setup.md |
| `convex_audit_diff` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-diff.md |
| `convex_audit_functions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-functions.md |
| `convex_audit_pagination` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-pagination.md |
| `convex_audit_query_efficiency` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-query-efficiency.md |
| `convex_audit_schedulers` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-schedulers.md |
| `convex_audit_schema` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-schema.md |
| `convex_audit_storage_usage` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-storage-usage.md |
| `convex_audit_vector_search` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-vector-search.md |
| `convex_bootstrap_project` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-bootstrap-project.md |
| `convex_check_crons` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-check-crons.md |
| `convex_check_env_vars` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-check-env-vars.md |
| `convex_check_function_refs` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-check-function-refs.md |
| `convex_check_type_safety` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-check-type-safety.md |
| `convex_check_validator_coverage` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-check-validator-coverage.md |
| `convex_critter_check` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-critter-check.md |
| `convex_discover_tools` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-discover-tools.md |
| `convex_export_sarif` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-export-sarif.md |
| `convex_get_methodology` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-get-methodology.md |
| `convex_scan_capabilities` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-scan-capabilities.md |
| `convex_search_gotchas` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-search-gotchas.md |
| `convex_snapshot_schema` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-snapshot-schema.md |
| `convex_suggest_indexes` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-suggest-indexes.md |
| `convex_verify_concept` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-verify-concept.md |
| `critter_check` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/critter-check.md |
| `crypto_price_historical` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/crypto-price-historical.md |
| `crypto_price_quote` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/crypto-price-quote.md |
| `csv_aggregate` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/csv-aggregate.md |
| `csv_select_rows` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/csv-select-rows.md |
| `decision_quality_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/decision-quality-scan.md |
| `deeptrace_check_permission` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-check-permission.md |
| `deeptrace_get_evidence_pack` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-get-evidence-pack.md |
| `deeptrace_get_passport` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-get-passport.md |
| `deeptrace_list_receipts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-list-receipts.md |
| `deeptrace_receipt_stats` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-receipt-stats.md |
| `deeptrace_search_evidence` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-search-evidence.md |
| `deeptrace_verify_receipt` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-verify-receipt.md |
| `delta_brief` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-brief.md |
| `delta_compare` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-compare.md |
| `delta_diligence` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-diligence.md |
| `delta_packets` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-packets.md |
| `delta_review` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-review.md |
| `delta_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-scan.md |
| `delta_watch` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-watch.md |
| `design_voice_pipeline` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/design-voice-pipeline.md |
| `detect_company_mode` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/detect-company-mode.md |
| `detect_contradictions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/detect-contradictions.md |
| `detect_repeated_questions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/detect-repeated-questions.md |
| `detect_subvertical` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/detect-subvertical.md |
| `detect_temporal_signal` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/detect-temporal-signal.md |
| `detect_vertical` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/detect-vertical.md |
| `diff_crawl` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/diff-crawl.md |
| `diff_outputs` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/diff-outputs.md |
| `diff_screenshots` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/diff-screenshots.md |
| `discover_infrastructure` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/discover-infrastructure.md |
| `discover_tools` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/discover-tools.md |
| `discover_vision_env` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/discover-vision-env.md |
| `distribution_surface_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/distribution-surface-scan.md |
| `dive_code_locate` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-code-locate.md |
| `dive_code_review` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-code-review.md |
| `dive_preflight` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-preflight.md |
| `dive_snapshot` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-snapshot.md |
| `dive_walkthrough` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-walkthrough.md |
| `economy_gdp` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/economy-gdp.md |
| `economy_inflation` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/economy-inflation.md |
| `enrich_entity` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/enrich-entity.md |
| `enrich_recon` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/enrich-recon.md |
| `entity_lookup` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/entity-lookup.md |
| `equity_fundamental_overview` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/equity-fundamental-overview.md |
| `equity_price_historical` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/equity-price-historical.md |
| `equity_price_quote` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/equity-price-quote.md |
| `evidence_gap_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/evidence-gap-scan.md |
| `export_audit_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/export-audit-report.md |
| `export_crunchbase_profile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/export-crunchbase-profile.md |
| `export_dimension_bundle` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/export-dimension-bundle.md |
| `export_pitchbook_profile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/export-pitchbook-profile.md |
| `export_yc_application_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/export-yc-application-context.md |
| `exportDocumentToMarkdown` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/exportdocumenttomarkdown.md |
| `extract_figma_frames` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-figma-frames.md |
| `extract_fractions_and_simplify_from_image` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-fractions-and-simplify-from-image.md |
| `extract_patent_claims` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-patent-claims.md |
| `extract_publication_metadata` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-publication-metadata.md |
| `extract_regulatory_artifacts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-regulatory-artifacts.md |
| `extract_structured_data` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-structured-data.md |
| `extract_trial_evidence` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-trial-evidence.md |
| `extract_variables` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/extract-variables.md |
| `fetch_rss_feeds` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/fetch-rss-feeds.md |
| `fetch_url` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/fetch-url.md |
| `financial_hygiene_check` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/financial-hygiene-check.md |
| `find_contradictions_for` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/find-contradictions-for.md |
| `findTools` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/findtools.md |
| `forecast_temporal_trend` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/forecast-temporal-trend.md |
| `founder_company_naming_pack` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-company-naming-pack.md |
| `founder_deep_context_gather` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-deep-context-gather.md |
| `founder_delegation_boundary_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-delegation-boundary-scan.md |
| `founder_direction_assessment` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-direction-assessment.md |
| `founder_gaps_detect` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-gaps-detect.md |
| `founder_local_gather` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-local-gather.md |
| `founder_materials_check` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-materials-check.md |
| `founder_next_unlocks` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-next-unlocks.md |
| `founder_ontrack_scorecard` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-ontrack-scorecard.md |
| `founder_packet_diff` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-packet-diff.md |
| `founder_packet_history_diff` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-packet-history-diff.md |
| `founder_packet_validate` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-packet-validate.md |
| `founder_readiness_score` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-readiness-score.md |
| `founder_stage_assess` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-stage-assess.md |
| `founder_target_customer_map` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-target-customer-map.md |
| `fusionSearch` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/fusionsearch.md |
| `generate_countermodels` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-countermodels.md |
| `generate_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-summary.md |
| `get_ab_test_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-ab-test-report.md |
| `get_active_forecasts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-active-forecasts.md |
| `get_agent_role` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-agent-role.md |
| `get_annual_retrospective` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-annual-retrospective.md |
| `get_autopilot_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-autopilot-status.md |
| `get_batch_run_history` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-batch-run-history.md |
| `get_benchmark_history` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-benchmark-history.md |
| `get_benchmark_oracles` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-benchmark-oracles.md |
| `get_benchmark_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-benchmark-report.md |
| `get_boilerplate_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-boilerplate-status.md |
| `get_causal_chain` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-causal-chain.md |
| `get_compaction_recovery` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-compaction-recovery.md |
| `get_company_truth` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-company-truth.md |
| `get_context_bundle` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-context-bundle.md |
| `get_daily_brief_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-daily-brief-summary.md |
| `get_daily_log` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-daily-log.md |
| `get_design_spec` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-design-spec.md |
| `get_design_violations` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-design-violations.md |
| `get_dimension_profile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-dimension-profile.md |
| `get_distribution_surfaces` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-distribution-surfaces.md |
| `get_dive_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-dive-report.md |
| `get_dive_tree` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-dive-tree.md |
| `get_dogfood_sessions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-dogfood-sessions.md |
| `get_dogfood_telemetry` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-dogfood-telemetry.md |
| `get_drift_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-drift-report.md |
| `get_engine_context_health` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-engine-context-health.md |
| `get_entity_graph_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-entity-graph-summary.md |
| `get_event_ledger` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-event-ledger.md |
| `get_failure_triage` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-failure-triage.md |
| `get_figma_design_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-figma-design-context.md |
| `get_flywheel_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-flywheel-status.md |
| `get_forecast_chain` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-forecast-chain.md |
| `get_forecast_evidence` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-forecast-evidence.md |
| `get_forecast_track_record` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-forecast-track-record.md |
| `get_founder_execution_order` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-founder-execution-order.md |
| `get_founder_job_topology` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-founder-job-topology.md |
| `get_founder_packet_resource` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-founder-packet-resource.md |
| `get_founder_progression_rubric` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-founder-progression-rubric.md |
| `get_gate_history` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-gate-history.md |
| `get_gate_preset` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-gate-preset.md |
| `get_important_changes` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-important-changes.md |
| `get_improvement_recommendations` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-improvement-recommendations.md |
| `get_ingest_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-ingest-status.md |
| `get_judge_history` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-judge-history.md |
| `get_latest_signals` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-latest-signals.md |
| `get_messaging_health` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-messaging-health.md |
| `get_monthly_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-monthly-report.md |
| `get_narrative_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-narrative-status.md |
| `get_observability_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-observability-summary.md |
| `get_openclaw_audit` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-openclaw-audit.md |
| `get_openclaw_delivery_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-openclaw-delivery-status.md |
| `get_openclaw_results` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-openclaw-results.md |
| `get_ops_dashboard` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-ops-dashboard.md |
| `get_packet_lineage` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-packet-lineage.md |
| `get_parallel_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-parallel-status.md |
| `get_policy_detail` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-policy-detail.md |
| `get_proactive_alerts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-proactive-alerts.md |
| `get_project_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-project-context.md |
| `get_quarterly_review` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-quarterly-review.md |
| `get_recon_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-recon-summary.md |
| `get_regression_gate` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-regression-gate.md |
| `get_repeat_cognition_metrics` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-repeat-cognition-metrics.md |
| `get_role_packet_defaults` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-role-packet-defaults.md |
| `get_self_directed_delivery_run` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-self-directed-delivery-run.md |
| `get_self_eval_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-self-eval-report.md |
| `get_sentinel_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-sentinel-report.md |
| `get_session_compliance` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-session-compliance.md |
| `get_session_journal` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-session-journal.md |
| `get_session_profile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-session-profile.md |
| `get_shared_context_packet` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-shared-context-packet.md |
| `get_shared_context_peer` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-shared-context-peer.md |
| `get_shared_context_snapshot` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-shared-context-snapshot.md |
| `get_signal_recommendations` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-signal-recommendations.md |
| `get_skill_risk_profile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-skill-risk-profile.md |
| `get_source_trust_policy` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-source-trust-policy.md |
| `get_state_diff_history` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-state-diff-history.md |
| `get_subconscious_hint` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-subconscious-hint.md |
| `get_sync_bridge_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-sync-bridge-status.md |
| `get_system_pulse` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-system-pulse.md |
| `get_tool_graph` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-tool-graph.md |
| `get_tool_quick_ref` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-tool-quick-ref.md |
| `get_trajectory_analysis` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-trajectory-analysis.md |
| `get_trajectory_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-trajectory-summary.md |
| `get_traversal_plan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-traversal-plan.md |
| `get_uptime_stats` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-uptime-stats.md |
| `get_usage_insights` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-usage-insights.md |
| `get_verification_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-verification-status.md |
| `get_view_capabilities` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-view-capabilities.md |
| `get_view_state` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-view-state.md |
| `get_watchdog_log` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-watchdog-log.md |
| `get_weekly_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-weekly-summary.md |
| `get_workflow_chain` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-workflow-chain.md |
| `get_workflow_history` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/get-workflow-history.md |
| `getArtifactsWithHealth` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getartifactswithhealth.md |
| `getCalibrationStats` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getcalibrationstats.md |
| `getCanaryRegressions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getcanaryregressions.md |
| `getCanaryTrend` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getcanarytrend.md |
| `getComparisonTrend` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getcomparisontrend.md |
| `getContradictoryPosts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getcontradictoryposts.md |
| `getDealFlow` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getdealflow.md |
| `getDocument` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getdocument.md |
| `getEntity` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getentity.md |
| `getEntityContext` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getentitycontext.md |
| `getEntityContextByName` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getentitycontextbyname.md |
| `getEntityContextStats` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getentitycontextstats.md |
| `getEntityInsights` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getentityinsights.md |
| `getEntityNetwork` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getentitynetwork.md |
| `getEvolutionDashboard` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getevolutiondashboard.md |
| `getFactById` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getfactbyid.md |
| `getFactsByRun` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getfactsbyrun.md |
| `getFastestGrowingRepos` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getfastestgrowingrepos.md |
| `getFolderWithDocuments` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getfolderwithdocuments.md |
| `getForYouFeed` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getforyoufeed.md |
| `getHoldings` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getholdings.md |
| `getHygieneReport` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/gethygienereport.md |
| `getInvestorProfile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getinvestorprofile.md |
| `getKnowledgeGraph` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getknowledgegraph.md |
| `getKnowledgeGraphClaims` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getknowledgegraphclaims.md |
| `getLatestDashboard` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getlatestdashboard.md |
| `getLatestPublicDossier` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getlatestpublicdossier.md |
| `getMethodology` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getmethodology.md |
| `getMigrationStats` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getmigrationstats.md |
| `getMission` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getmission.md |
| `getMissionByKey` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getmissionbykey.md |
| `getMissionDashboard` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getmissiondashboard.md |
| `getModelCostSummary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getmodelcostsummary.md |
| `getOpenDisputes` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getopendisputes.md |
| `getPendingRoutingRecommendations` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getpendingroutingrecommendations.md |
| `getPendingSniffChecks` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getpendingsniffchecks.md |
| `getPersonProfile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getpersonprofile.md |
| `getPlan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getplan.md |
| `getPublicThreads` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getpublicthreads.md |
| `getSignalTimeseries` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getsignaltimeseries.md |
| `getSloMetricsSummary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getslometricssummary.md |
| `getSourceRegistry` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getsourceregistry.md |
| `getSpreadsheetRange` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getspreadsheetrange.md |
| `getStakeholderGraph` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getstakeholdergraph.md |
| `getTasksForMission` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/gettasksformission.md |
| `getThread` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getthread.md |
| `getThreadPosts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getthreadposts.md |
| `getThreadsByEntity` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getthreadsbyentity.md |
| `getThreadStats` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getthreadstats.md |
| `getThreadsWithEvents` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getthreadswithevents.md |
| `getTrendingRepos` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/gettrendingrepos.md |
| `getVerificationsForFact` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getverificationsforfact.md |
| `getVerificationSummary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/getverificationsummary.md |
| `grade_agent_run` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/grade-agent-run.md |
| `grade_fraction_quiz_from_image` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/grade-fraction-quiz-from-image.md |
| `graphify_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/graphify-report.md |
| `graphify_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/graphify-status.md |
| `heartbeat_shared_context_peer` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/heartbeat-shared-context-peer.md |
| `hiring_gap_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/hiring-gap-scan.md |
| `ingest_claude_code_sessions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/ingest-claude-code-sessions.md |
| `ingest_codebase_changes` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/ingest-codebase-changes.md |
| `inject_context_into_prompt` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/inject-context-into-prompt.md |
| `inspect_topology_shape` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/inspect-topology-shape.md |
| `invalidate_shared_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/invalidate-shared-context.md |
| `investigate` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/investigate.md |
| `json_select` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/json-select.md |
| `judge_verify_subtask` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/judge-verify-subtask.md |
| `list_agent_tasks` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-agent-tasks.md |
| `list_available_toolsets` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-available-toolsets.md |
| `list_available_views` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-available-views.md |
| `list_contradictions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-contradictions.md |
| `list_dimension_evidence` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-dimension-evidence.md |
| `list_dimension_interactions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-dimension-interactions.md |
| `list_dimension_snapshots` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-dimension-snapshots.md |
| `list_driver_tools` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-driver-tools.md |
| `list_eval_runs` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-eval-runs.md |
| `list_extracted_skill_templates` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-extracted-skill-templates.md |
| `list_founder_issue_packets` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-founder-issue-packets.md |
| `list_learnings` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-learnings.md |
| `list_openclaw_channels` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-openclaw-channels.md |
| `list_pending_sync_operations` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-pending-sync-operations.md |
| `list_sandbox_policies` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-sandbox-policies.md |
| `list_self_directed_delivery_runs` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-self-directed-delivery-runs.md |
| `list_shared_context_peers` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-shared-context-peers.md |
| `list_skills` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-skills.md |
| `list_stale_packets` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-stale-packets.md |
| `list_verification_cycles` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-verification-cycles.md |
| `list_webmcp_tools` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-webmcp-tools.md |
| `list_workspace` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/list-workspace.md |
| `listAgentMemory` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/listagentmemory.md |
| `listDocuments` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/listdocuments.md |
| `listEntityContexts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/listentitycontexts.md |
| `listFiles` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/listfiles.md |
| `listFolders` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/listfolders.md |
| `listSpreadsheets` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/listspreadsheets.md |
| `load_diligence_pack` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/load-diligence-pack.md |
| `load_session_notes` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/load-session-notes.md |
| `log_context_budget` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/log-context-budget.md |
| `log_tool_call` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/log-tool-call.md |
| `lookup_entity` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/lookup-entity.md |
| `meeting_notes_extract_decisions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/meeting-notes-extract-decisions.md |
| `mine_session_patterns` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/mine-session-patterns.md |
| `monitor_repo` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/monitor-repo.md |
| `multi_criteria_score` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/multi-criteria-score.md |
| `nb_filter_receipts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-filter-receipts.md |
| `nb_filter_tool_activity` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-filter-tool-activity.md |
| `nb_get_feed_items` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-get-feed-items.md |
| `nb_get_funding_brief` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-get-funding-brief.md |
| `nb_get_leaderboard` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-get-leaderboard.md |
| `nb_get_qa_results` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-get-qa-results.md |
| `nb_get_signals` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-get-signals.md |
| `nb_list_agents` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-list-agents.md |
| `nb_list_escalated_actions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-list-escalated-actions.md |
| `nb_list_scenarios` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-list-scenarios.md |
| `nb_open_delegation` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-open-delegation.md |
| `nb_open_receipts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-open-receipts.md |
| `nb_review_pending_approvals` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-review-pending-approvals.md |
| `nb_review_shared_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-review-shared-context.md |
| `nb_search_from_chat` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-search-from-chat.md |
| `nb_search_reports` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-search-reports.md |
| `nb_search_research` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-search-research.md |
| `nb_view_screenshots` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-view-screenshots.md |
| `news_company` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/news-company.md |
| `news_world` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/news-world.md |
| `nodebench_get_app_state` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-get-app-state.md |
| `nodebench_get_capabilities` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-get-capabilities.md |
| `nodebench_get_digest` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-get-digest.md |
| `nodebench_get_screen_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-get-screen-context.md |
| `nodebench_list_views` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-list-views.md |
| `nodebench_query_elements` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-query-elements.md |
| `nodebench_search` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-search.md |
| `nodebench_search_views` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-search-views.md |
| `nodebench_traverse_feed` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-traverse-feed.md |
| `nodebench.activity_timeline` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.activity-timeline.md |
| `nodebench.compile_interview_packet` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.compile-interview-packet.md |
| `nodebench.context.pack` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.context.pack.md |
| `nodebench.dossiers.get` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.dossiers.get.md |
| `nodebench.entities.resolve` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.entities.resolve.md |
| `nodebench.expand_resource` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.expand-resource.md |
| `nodebench.expand_subject` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.expand-subject.md |
| `nodebench.get_entity_dossier` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.get-entity-dossier.md |
| `nodebench.get_matching_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.get-matching-context.md |
| `nodebench.refresh_resource` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.refresh-resource.md |
| `nodebench.render_output` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.render-output.md |
| `nodebench.report_export_preview` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.report-export-preview.md |
| `nodebench.research_company` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.research-company.md |
| `nodebench.research_person` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.research-person.md |
| `nodebench.search_public_sources` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.search-public-sources.md |
| `open_operating_dashboard` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/open-operating-dashboard.md |
| `overstory_fleet_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/overstory-fleet-status.md |
| `overstory_mail_log` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/overstory-mail-log.md |
| `overstory_merge_queue` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/overstory-merge-queue.md |
| `overstory_qa_summary` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/overstory-qa-summary.md |
| `partnership_target_map` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/partnership-target-map.md |
| `pdf_search_text` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/pdf-search-text.md |
| `populate_historicals` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/populate-historicals.md |
| `predict_risks_from_patterns` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/predict-risks-from-patterns.md |
| `pull_profile` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/pull-profile.md |
| `pull_report` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/pull-report.md |
| `pull_shared_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/pull-shared-context.md |
| `query_daily_brief` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/query-daily-brief.md |
| `query_funding_entities` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/query-funding-entities.md |
| `query_graphify` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/query-graphify.md |
| `query_research_queue` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/query-research-queue.md |
| `query_temporal_signals` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/query-temporal-signals.md |
| `query_view_data` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/query-view-data.md |
| `quickSearch` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/quicksearch.md |
| `rank_interventions` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/rank-interventions.md |
| `read_csv_file` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-csv-file.md |
| `read_docx_text` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-docx-text.md |
| `read_emails` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-emails.md |
| `read_image_ocr_text` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-image-ocr-text.md |
| `read_json_file` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-json-file.md |
| `read_jsonl_file` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-jsonl-file.md |
| `read_pdf_text` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-pdf-text.md |
| `read_pptx_text` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-pptx-text.md |
| `read_text_file` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-text-file.md |
| `read_workspace_file` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-workspace-file.md |
| `read_xlsx_file` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/read-xlsx-file.md |
| `readAgentMemory` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/readagentmemory.md |
| `refresh_subconscious` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/refresh-subconscious.md |
| `refresh_task_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/refresh-task-context.md |
| `render_decision_memo` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/render-decision-memo.md |
| `research_job_market` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/research-job-market.md |
| `resolveAlias` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/resolvealias.md |
| `retention_get_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/retention-get-status.md |
| `retention_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/retention-status.md |
| `review_paper_as_reviewer` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/review-paper-as-reviewer.md |
| `review_pr_checklist` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/review-pr-checklist.md |
| `route_founder_packet` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/route-founder-packet.md |
| `runway_check` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/runway-check.md |
| `sandbox_search` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/sandbox-search.md |
| `sandbox_stats` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/sandbox-stats.md |
| `scan_capabilities` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scan-capabilities.md |
| `scan_dependencies` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scan-dependencies.md |
| `scan_terminal_security` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scan-terminal-security.md |
| `scan_webmcp_origin` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scan-webmcp-origin.md |
| `scan_wordpress_updates` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scan-wordpress-updates.md |
| `score_compounding` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/score-compounding.md |
| `score_scenario_branch` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/score-scenario-branch.md |
| `scrapling_batch_fetch` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scrapling-batch-fetch.md |
| `scrapling_crawl_status` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scrapling-crawl-status.md |
| `scrapling_extract` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scrapling-extract.md |
| `scrapling_fetch` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scrapling-fetch.md |
| `scrapling_track_element` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/scrapling-track-element.md |
| `search` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search.md |
| `search_all_knowledge` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search-all-knowledge.md |
| `search_content_archive` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search-content-archive.md |
| `search_github` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search-github.md |
| `search_learnings` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search-learnings.md |
| `search_memory` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search-memory.md |
| `search_openclaw_gotchas` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search-openclaw-gotchas.md |
| `search_report_context` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/search-report-context.md |
| `searchDocuments` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/searchdocuments.md |
| `searchEntities` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/searchentities.md |
| `searchEntityContexts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/searchentitycontexts.md |
| `searchResearch` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/searchresearch.md |
| `searchThreads` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/searchthreads.md |
| `seo_audit_url` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/seo-audit-url.md |
| `service_to_dashboard_path` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/service-to-dashboard-path.md |
| `setup_local_env` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/setup-local-env.md |
| `share_get_packet_link` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/share-get-packet-link.md |
| `shortest_valid_path` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/shortest-valid-path.md |
| `solve_bass_clef_age_from_image` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/solve-bass-clef-age-from-image.md |
| `solve_green_polygon_area_from_image` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/solve-green-polygon-area-from-image.md |
| `solve_red_green_deviation_average_from_image` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/solve-red-green-deviation-average-from-image.md |
| `solve_storage_upgrade_cost_per_file_from_image` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/solve-storage-upgrade-cost-per-file-from-image.md |
| `submission_readiness_score` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/submission-readiness-score.md |
| `suggest_optimizations` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/suggest-optimizations.md |
| `suggest_related` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/suggest-related.md |
| `suggest_tests` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/suggest-tests.md |
| `summarize_session` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/summarize-session.md |
| `sync_figma_tokens` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/sync-figma-tokens.md |
| `team_alignment_check` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/team-alignment-check.md |
| `thompson_anti_elitism_lint` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/thompson-anti-elitism-lint.md |
| `thompson_feynman_edit` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/thompson-feynman-edit.md |
| `thompson_quality_gate` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/thompson-quality-gate.md |
| `thompson_visual_map` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/thompson-visual-map.md |
| `toon_decode` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/toon-decode.md |
| `toon_encode` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/toon-encode.md |
| `track_entity_changes` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/track-entity-changes.md |
| `translate_academic` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/translate-academic.md |
| `traverse_entity_graph` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/traverse-entity-graph.md |
| `traverse_feed` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/traverse-feed.md |
| `validate_shortcut` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/validate-shortcut.md |
| `verify_concept_support` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/verify-concept-support.md |
| `watchlist_get_alerts` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/watchlist-get-alerts.md |
| `watchlist_list_entities` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/watchlist-list-entities.md |
| `web_search` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/web-search.md |
| `workflow_adoption_scan` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/workflow-adoption-scan.md |
| `xlsx_aggregate` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/xlsx-aggregate.md |
| `xlsx_select_rows` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/xlsx-select-rows.md |
| `zip_list_files` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/zip-list-files.md |
| `zip_read_text_file` | Read | Low | https://policylayer.com/tools/io-github-homenshum-nodebench/zip-read-text-file.md |
| `accept_shared_task` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/accept-shared-task.md |
| `ack_shared_context` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/ack-shared-context.md |
| `add_forecast_evidence` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/add-forecast-evidence.md |
| `add_rss_source` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/add-rss-source.md |
| `addDocumentToFolder` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/adddocumenttofolder.md |
| `archive_content` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/archive-content.md |
| `assign_agent_role` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/assign-agent-role.md |
| `attach_execution_evidence` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/attach-execution-evidence.md |
| `bind_local_account` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/bind-local-account.md |
| `bootstrap_project` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/bootstrap-project.md |
| `broadcast_agent_update` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/broadcast-agent-update.md |
| `build_before_after_memo` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/build-before-after-memo.md |
| `build_causal_chain` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/build-causal-chain.md |
| `build_company_packet` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/build-company-packet.md |
| `build_slack_onepager` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/build-slack-onepager.md |
| `claim_agent_task` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/claim-agent-task.md |
| `claimTask` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/claimtask.md |
| `compile_environment_spec` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/compile-environment-spec.md |
| `complete_autonomy_benchmark` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/complete-autonomy-benchmark.md |
| `complete_eval_run` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/complete-eval-run.md |
| `complete_execution_run` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/complete-execution-run.md |
| `complete_shared_task` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/complete-shared-task.md |
| `compress_or_expand_text` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/compress-or-expand-text.md |
| `compute_dimension_profile` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/compute-dimension-profile.md |
| `configure_channel_preferences` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/configure-channel-preferences.md |
| `configure_sandbox_policy` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/configure-sandbox-policy.md |
| `convex_audit_transaction_safety` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-audit-transaction-safety.md |
| `convex_generate_plan` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-generate-plan.md |
| `convex_generate_rules_md` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-generate-rules-md.md |
| `convex_record_gotcha` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-record-gotcha.md |
| `convex_schema_migration_plan` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/convex-schema-migration-plan.md |
| `create_forecast` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/create-forecast.md |
| `create_proof_pack` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/create-proof-pack.md |
| `create_task_bank` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/create-task-bank.md |
| `create_visual_pr` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/create-visual-pr.md |
| `createDocument` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/createdocument.md |
| `createDocumentWithContent` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/createdocumentwithcontent.md |
| `createFolder` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/createfolder.md |
| `createMission` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/createmission.md |
| `createPlan` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/createplan.md |
| `createSpreadsheet` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/createspreadsheet.md |
| `decide_re_update` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/decide-re-update.md |
| `deeptrace_create_evidence_pack` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-create-evidence-pack.md |
| `deeptrace_create_passport` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-create-passport.md |
| `deeptrace_ingest_evidence` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-ingest-evidence.md |
| `deeptrace_log_receipt` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/deeptrace-log-receipt.md |
| `delegate_founder_issue` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/delegate-founder-issue.md |
| `delta_handoff` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-handoff.md |
| `delta_memo` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-memo.md |
| `delta_retain` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/delta-retain.md |
| `dismiss_alert` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/dismiss-alert.md |
| `dive_changelog` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-changelog.md |
| `dive_design_issue` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-design-issue.md |
| `dive_generate_tests` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-generate-tests.md |
| `dive_link_backend` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-link-backend.md |
| `dive_record_test_step` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-record-test-step.md |
| `dive_save_screenshot` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/dive-save-screenshot.md |
| `draft_email_reply` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/draft-email-reply.md |
| `duplicateDocument` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/duplicatedocument.md |
| `end_component_flow` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/end-component-flow.md |
| `end_dogfood_session` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/end-dogfood-session.md |
| `escalate_shared_task` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/escalate-shared-task.md |
| `export_artifact_packet` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/export-artifact-packet.md |
| `flag_important_change` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/flag-important-change.md |
| `founder_local_synthesize` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/founder-local-synthesize.md |
| `generate_academic_caption` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-academic-caption.md |
| `generate_flicker_report` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-flicker-report.md |
| `generate_grid_collage` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-grid-collage.md |
| `generate_implementation_plan` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-implementation-plan.md |
| `generate_parallel_agents_md` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-parallel-agents-md.md |
| `generate_plan_delegation_packet` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-plan-delegation-packet.md |
| `generate_pr_report` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-pr-report.md |
| `generate_proposal_memo` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-proposal-memo.md |
| `generate_report` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-report.md |
| `generate_self_instructions` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-self-instructions.md |
| `generate_team_install_plan` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-team-install-plan.md |
| `generate_voice_scaffold` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-voice-scaffold.md |
| `generate_zero_draft` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/generate-zero-draft.md |
| `graphify_import_to_subconscious` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/graphify-import-to-subconscious.md |
| `ingest_dive_screenshots` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/ingest-dive-screenshots.md |
| `ingest_temporal_observation` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/ingest-temporal-observation.md |
| `ingest_upload` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/ingest-upload.md |
| `install_nodebench_plugin` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/install-nodebench-plugin.md |
| `judge_session` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/judge-session.md |
| `link_durable_objects` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/link-durable-objects.md |
| `log_benchmark_milestone` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/log-benchmark-milestone.md |
| `log_gap` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/log-gap.md |
| `log_phase_findings` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/log-phase-findings.md |
| `log_recon_finding` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/log-recon-finding.md |
| `log_test_result` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/log-test-result.md |
| `manage_implementation_packets` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/manage-implementation-packets.md |
| `manage_task_list` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/manage-task-list.md |
| `merge_compose_output` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/merge-compose-output.md |
| `merge_research_results` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/merge-research-results.md |
| `nb_open_approval_queue` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nb-open-approval-queue.md |
| `nodebench_create_document` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench-create-document.md |
| `nodebench.capture` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.capture.md |
| `nodebench.claims.submit_public` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.claims.submit-public.md |
| `nodebench.link_private_signal_to_public_entity` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.link-private-signal-to-public-entity.md |
| `nodebench.notebook_append` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.notebook-append.md |
| `nodebench.report_export_complete` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.report-export-complete.md |
| `nodebench.submit_public_claim` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.submit-public-claim.md |
| `nodebench.watch_entity` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/nodebench.watch-entity.md |
| `open_core_boundary_advisor` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/open-core-boundary-advisor.md |
| `plan_decompose_mission` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/plan-decompose-mission.md |
| `polish_academic_text` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/polish-academic-text.md |
| `promote_to_eval` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/promote-to-eval.md |
| `propose_shared_task` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/propose-shared-task.md |
| `publish_founder_issue_packet` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/publish-founder-issue-packet.md |
| `publish_shared_context` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/publish-shared-context.md |
| `publish_to_queue` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/publish-to-queue.md |
| `queue_sync_operation` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/queue-sync-operation.md |
| `rate_packet_usefulness` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/rate-packet-usefulness.md |
| `record_dogfood_telemetry` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-dogfood-telemetry.md |
| `record_eval_result` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-eval-result.md |
| `record_event` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-event.md |
| `record_execution_decision` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-execution-decision.md |
| `record_execution_step` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-execution-step.md |
| `record_execution_verification` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-execution-verification.md |
| `record_fix_attempt` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-fix-attempt.md |
| `record_learning` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-learning.md |
| `record_manual_correction` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-manual-correction.md |
| `record_openclaw_gotcha` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-openclaw-gotcha.md |
| `record_path_step` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-path-step.md |
| `record_provenance_receipt` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-provenance-receipt.md |
| `record_repeated_question` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-repeated-question.md |
| `record_state_diff` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-state-diff.md |
| `record_sync_artifact` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-sync-artifact.md |
| `record_sync_outcome` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/record-sync-outcome.md |
| `recordCanaryRun` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/recordcanaryrun.md |
| `register_component` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/register-component.md |
| `register_shared_context_peer` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/register-shared-context-peer.md |
| `register_skill` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/register-skill.md |
| `reject_shared_task` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/reject-shared-task.md |
| `release_agent_task` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/release-agent-task.md |
| `remove_ai_signatures` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/remove-ai-signatures.md |
| `report` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/report.md |
| `resolve_forecast` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/resolve-forecast.md |
| `resolve_founder_issue` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/resolve-founder-issue.md |
| `resolve_gap` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/resolve-gap.md |
| `resolveRoutingRecommendation` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/resolveroutingrecommendation.md |
| `resolveSniffCheck` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/resolvesniffcheck.md |
| `restoreDocument` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/restoredocument.md |
| `retention_register_connection` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/retention-register-connection.md |
| `retention_sync` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/retention-sync.md |
| `retention_sync_findings` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/retention-sync-findings.md |
| `sandbox_ingest` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sandbox-ingest.md |
| `save_research_resource` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/save-research-resource.md |
| `save_session_note` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/save-session-note.md |
| `scaffold_directory` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/scaffold-directory.md |
| `scaffold_nodebench_project` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/scaffold-nodebench-project.md |
| `scaffold_openclaw_project` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/scaffold-openclaw-project.md |
| `scaffold_openclaw_sandbox` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/scaffold-openclaw-sandbox.md |
| `scaffold_research_pipeline` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/scaffold-research-pipeline.md |
| `send_agent_message` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/send-agent-message.md |
| `send_email` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/send-email.md |
| `send_openclaw_message` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/send-openclaw-message.md |
| `send_peer_message` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/send-peer-message.md |
| `sendMessage` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sendmessage.md |
| `set_watchdog_config` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/set-watchdog-config.md |
| `setup_operator_profile` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/setup-operator-profile.md |
| `share_create_packet_link` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/share-create-packet-link.md |
| `sniff_record_human_review` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sniff-record-human-review.md |
| `start_component_flow` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/start-component-flow.md |
| `summarize` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/summarize.md |
| `sync_company` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sync-company.md |
| `sync_daily_brief` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sync-daily-brief.md |
| `sync_operator_profile` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sync-operator-profile.md |
| `sync_report` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sync-report.md |
| `sync_skill` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/sync-skill.md |
| `synthesize_extension_plan` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/synthesize-extension-plan.md |
| `synthesize_feature_plan` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/synthesize-feature-plan.md |
| `synthesize_integration_proposal` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/synthesize-integration-proposal.md |
| `synthesize_recon_to_learnings` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/synthesize-recon-to-learnings.md |
| `tag_ui_bug` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/tag-ui-bug.md |
| `thompson_write` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/thompson-write.md |
| `track` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/track.md |
| `track_action` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/track-action.md |
| `track_intent` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/track-intent.md |
| `track_milestone` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/track-milestone.md |
| `update_agents_md` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/update-agents-md.md |
| `update_company_truth` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/update-company-truth.md |
| `update_forecast_probability` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/update-forecast-probability.md |
| `updateDocument` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/updatedocument.md |
| `updatePlanStep` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/updateplanstep.md |
| `upsert_durable_object` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/upsert-durable-object.md |
| `upsertEntity` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/upsertentity.md |
| `watchlist_add_entity` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/watchlist-add-entity.md |
| `watchlist_refresh_entities` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/watchlist-refresh-entities.md |
| `write_workspace_file` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/write-workspace-file.md |
| `writeAgentMemory` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/writeagentmemory.md |
| `zip_extract_file` | Write | Medium | https://policylayer.com/tools/io-github-homenshum-nodebench/zip-extract-file.md |

## Tool descriptions

- `abandon_cycle` — Abandon an active verification cycle that will not be completed. Use this to clean up orphaned or stale cycles.
- `archiveDocument` — Archive (soft-delete) a document and all its children recursively.
- `cleanup_stale_runs` — Clean up orphaned eval runs stuck in
- `deeptrace_revoke_passport` — Revoke an agent
- `delete_learning` — Delete a learning by key. Use when a learning is outdated or incorrect.
- `delete_sandbox_policy` — Delete a sandbox policy. Fails if any active sessions are using it.
- `deleteAgentMemory` — Delete stored memory by key
- `removeDocumentFromFolder` — Remove a document from a folder.
- `share_revoke_packet_link` — Revoke a local share link so it no longer counts as active.
- `unload_toolset` — Remove a dynamically loaded toolset from the current session to free up context. Cannot unload toolsets from the initial preset.
- `benchmark_models` — Run the same prompt against multiple LLM providers and compare responses. Returns side-by-side results with latency, token usage, and a summary. Useful for model selection, quality comparison, and cost analysis.
- `bootstrap_parallel_agents` — Detect whether a target project repo has parallel agent infrastructure and, if not, scaffold everything needed. Scans for task coordination, role configs, oracle testing, context budget tracking, progress files, AGENTS.md parallel sectio…
- `build_banking_packet` — Build a banker-readiness packet from the canonical company packet.
- `build_company_profile_starter` — Build a starter PitchBook/Crunchbase-like company profile.
- `build_founder_operating_model` — Build the complete founder operating model: execution order, queue topology, packet routing, source trust policy, progression rubric, and benchmark oracles.
- `build_research_digest` — Generate a digest of new (unseen) articles from RSS feeds. Compares against previously seen articles via SQLite. Returns only new items grouped by category. After generating, articles are marked as seen so the next digest only shows trul…
- `build_shared_context_subscription` — Build the exact pull/subscription manifest an agent client should use to watch a packet or packet scope.
- `build_shared_context_subscription_manifest` — Build a filtered snapshot/events/pull manifest for one peer, packet class, producer, scope, or subject so clients can subscribe to only relevant shared-context updates.
- `build_submission_export` — Build a generic submission export from the canonical company packet.
- `build_temporal_graph` — Build a temporal relationship graph for an entity.
- `burst_capture` — Capture N sequential screenshots at fixed intervals using Playwright.
- `call_driver_tool` — Invoke a tool on a connected MCP driver. This proxies the call to the external MCP server (e.g. playwright-mcp or mobile-mcp) and returns the result. Use list_driver_tools to see available tools and their parameters first.
- `call_llm` — Call an LLM model directly and get the response with metrics (tokens, latency). Uses available API keys: Gemini → OpenAI → Anthropic. Useful for eval-driven workflows, model comparison, structured analysis, and any task where the agent n…
- `call_openclaw_skill` — Run an OpenClaw skill safely through security checks.
- `call_webmcp_tool` — Invoke a WebMCP tool on a connected origin. The tool is executed in the browser page context via page.evaluate(). Args are validated for suspicious patterns and results are scanned for anomalies. Use list_webmcp_tools to see available to…
- `capture_surface_stats` — Capture Android SurfaceFlinger stats and logcat for jank analysis (Layer 0 only). Returns janky frame counts, missed vsync, slow UI thread metrics, and filtered logcat entries from Choreographer, SurfaceFlinger, WindowManager, ActivityMa…
- `capture_ui_screenshot` — Capture a screenshot of a URL using headless Playwright. Returns the screenshot as an inline image that multimodal agents can see and evaluate directly. Also captures browser console errors. Supports viewport presets (mobile/tablet/deskt…
- `compile_decision_packet` — Compile entity intelligence into a decision-ready packet.
- `compile_scenarios` — Generate 3-7 future scenario branches for an entity or decision.
- `compile_tension_model` — Model explicit tensions between forces for a decision or entity.
- `compute_ssim_analysis` — Compute block-based SSIM analysis on a set of frame images. Uses 8x8 blocks with parallel ProcessPoolExecutor. Returns SSIM scores, adaptive threshold (max(0.70, median - 2*std)), flicker classification (rapid_oscillation / sustained_cha…
- `connect_mcp_driver` — Connect to an external MCP server and make its tools available through nodebench-mcp. Predefined drivers:
- `connect_openclaw` — Connect to an OpenClaw agent with a security policy applied.
- `connect_webmcp_origin` — Connect to a WebMCP-enabled website via Playwright. Navigates to the URL, intercepts navigator.modelContext tool registrations, and makes discovered tools available for invocation via call_webmcp_tool. Requires Playwright (npm install pl…
- `convex_pre_deploy_gate` — Run a comprehensive pre-deployment quality gate. Checks: convex/ directory structure, schema.ts validity, deprecated validator usage, auth configuration, recent audit results, and project initialization status. Returns pass/fail with spe…
- `convex_quality_gate` — Run a configurable quality gate across all stored audit results. Like SonarQube
- `delta_self_dogfood` — Dogfood NodeBench Delta on itself. Verifies runtime health, setup friction, distribution surfaces, and compounding return loops, then emits a repair-ready delta.market packet.
- `disconnect_driver` — Disconnect from an external MCP driver and shut down its child process. Use this to clean up or to reconnect with different settings.
- `disconnect_openclaw` — Disconnect an OpenClaw session and generate a safety summary.
- `disconnect_webmcp_origin` — Disconnect from a WebMCP origin and close the browser page. Use this to clean up resources or to reconnect with different settings.
- `dive_auto_discover` — Scan the current page DOM and auto-register components in the dive tree. Discovers semantic landmarks (nav, header, footer, forms, modals, tables, sidebars) and counts interactive elements within each. Useful after navigating to a new pa…
- `dive_fix_verify` — After fixing a bug, verify the fix by re-navigating to the affected route, comparing before/after state, and updating the bug status + changelog. This is the core flywheel step: Bug tagged → Code located → Code fixed → Fix verified → Cha…
- `dive_interaction_test` — Define and track a structured interaction test for a component. Provide preconditions and a sequence of test steps (action, target, expected outcome). The agent executes each step via the MCP Bridge (browser_click, browser_type, etc.), t…
- `dive_reexplore` — Re-traverse a route after code changes to detect regressions and verify fixes. Compares the current state against previously registered components, bugs, and test results for that route. The agent should navigate to the route first (via …
- `end_openclaw_session` — End an OpenClaw session and generate a safety summary.
- `enforce_merge_gate` — Pre-merge validation combining git state, verification cycles, eval runs, test results, and quality gates. Returns a go/no-go merge decision with detailed check results and blocking issues. Use before merging any branch.
- `extract_video_frames` — Record screen and extract key frames from an Android device (Layers 1+2). Uses adb screenrecord then ffmpeg scene-filtered JPEG extraction. CRITICAL: uses -pix_fmt yuvj420p for ffmpeg 8.x compatibility. Falls back to regular fps extracti…
- `founder_local_weekly_reset` — One-call convenience: gathers all local context and produces a complete
- `get_path_replay` — Replay a session
- `gtm_script_builder` — Build a starter GTM script for the current founder wedge.
- `invoke_openclaw_skill` — Run an OpenClaw tool safely through security checks.
- `invoke_view_tool` — Invoke a per-view tool on the current or specified view.
- `judge_request_retry` — Request a retry, re-plan, escalation, or stop for a failed subtask.
- `judge_tool_output` — Run the 7-criterion LLM judge on a tool
- `load_toolset` — Dynamically load a toolset into the current session. After loading, the tools become immediately available for use. Based on the
- `log_interaction` — Log and optionally auto-execute an interaction step. If the built-in Playwright browser is active (launched by start_ui_dive), the action is automatically executed in the browser — just provide a CSS selector in
- `manipulate_screenshot` — Manipulate a screenshot using sharp (image processing). Supports crop (extract a region), resize, and annotate (draw colored rectangles and labels to highlight areas). Use after analyze_screenshot identifies regions of interest, or to pr…
- `navigate_to_view` — Navigate to a specific view in the NodeBench AI frontend.
- `nb_start_agent` — Start a new agent conversation with an optional initial message.
- `nb_switch_research_tab` — Switch the research hub tab.
- `nodebench_ask_agent` — Send a question to the NodeBench AI agent. Returns a structured response with reasoning and sources.
- `nodebench_navigate` — Navigate to a specific view. Returns the target view
- `nodebench.claims.verify` — Re-run deterministic public/private boundary and source-evidence verification for a stored public claim.
- `nodebench.research_role` — Run or reuse public role research, store public hiring or market claims, and return a compact role dossier.
- `nodebench.research_run` — Run adaptive, evidence-backed research across one or more subjects. Automatically resolves entities, infers scenario facets, selects relevant research angles, reuses precomputed resources when available, refreshes stale artifacts when ne…
- `open_dive_dashboard` — Open the NodeBench UI Dive dashboard in a browser. Shows the full flywheel cycle:
- `open_local_dashboard` — Start the local Daily Brief dashboard server if needed, and return the URL. The dashboard shows Brief metrics, Narrative thread lanes, and Ops status — all from local SQLite.
- `project_financials` — Build 5-year financial projections based on historical data and industry assumptions. Projects: - Revenue with declining growth rates - Operating expenses (gross margin, SG&A, R&D) - EBITDA and EBIT - Free cash flow (FCF) Uses template d…
- `readiness_scan` — Run a founder readiness scan against the progression and diligence model.
- `render_flow_visualization` — Render flow visualization with colored bounding boxes for each flow group. Supports overlay on a rendered page image or synthetic dark canvas fallback. Handles wide Figma pages (>3:1 aspect ratio) and uses cross-platform fonts (Windows/m…
- `request_execution_approval` — Request a human approval gate for a risky execution-trace action. Approval state is written onto the live run so the UI and ledger can show the pending handoff.
- `run_autonomous_loop` — Execute autonomous verification loop with stop conditions. Implements Ralph Wiggum pattern with checkpoints, iteration limits, and timeout. Use for multi-step autonomous tasks that need guardrails.
- `run_benchmark_batch` — Run a longitudinal benchmark batch. N=1 is a smoke test (1 founder, 1 session).
- `run_browserstack_benchmark_lane` — Return a BrowserStack/browser-automation benchmark lane payload.
- `run_closed_loop` — Track a compile-lint-test-debug closed loop iteration. Record the result of each step. Never present changes without a full green loop.
- `run_code_analysis` — Static analysis on code or text content for security issues, secrets, homograph attacks, ANSI injections, suspicious URLs, and code quality. Returns structured findings with severity, line numbers, and remediation. Works on any text cont…
- `run_competitor_signal_benchmark` — Return a competitor-signal-to-response benchmark lane payload.
- `run_deep_sim` — Run a multi-agent scenario simulation with bounded branching and budget controls. Instantiates agents with personas and incentives, varies conditions across branches, and generates an analytical report with convergence metrics.
- `run_dogfood_batch_with_judge` — Execute the priority 3 dogfood scenarios with automatic LLM judge validation.
- `run_entity_intelligence_mission` — Run a full DeepTrace entity intelligence mission with optional bounded research cell. Unifies relationship mapping, ownership, supply chain, signals, and causal analysis. Pass researchCell=true for threshold-driven re-analysis when the i…
- `run_flicker_detection` — Run full 4-layer Android UI flicker detection pipeline: SurfaceFlinger stats + logcat (L0), screenrecord (L1), frame extraction + SSIM analysis with adaptive threshold (L2), optional semantic verification (L3). Returns FlickerReport with…
- `run_founder_autonomy_benchmark` — Run the weekly founder reset autonomy benchmark lane.
- `run_graphify` — Generate a knowledge graph from a folder of code, docs, papers, or images.
- `run_judge_loop` — Execute a full judge-fix-verify loop: calls a tool, judges the output, and if it fails,
- `run_mandatory_flywheel` — Enforce the mandatory 6-step AI Flywheel verification after any non-trivial change. All 6 steps must pass before work is considered done. Skipping is only allowed for trivial changes (typo, comment, config) with explicit justification. R…
- `run_oracle_comparison` — Compare actual output against a known-good oracle reference. Based on Anthropic\
- `run_packet_to_implementation_benchmark` — Return a packet-to-implementation benchmark lane payload.
- `run_quality_gate` — Evaluate content or code against a set of boolean rules. Returns pass/fail with specific failures listed. The agent evaluates each rule and passes boolean results — the tool persists and aggregates.
- `run_recon` — Start a reconnaissance research session. Use this at the start of Phase 1 (Context Gathering) to organize research into external sources (SDKs, APIs, blogs) AND internal context (codebase, project details, existing patterns). Returns a s…
- `run_research_cell` — Run a bounded re-analysis cell for a DeepTrace entity investigation. Queries existing DeepTrace state through parallel branches (evidence gap analysis, counter-hypothesis, dimension coverage, source diversification) to surface gaps and w…
- `run_self_directed_delivery_loop` — Run a local-first autonomous delivery loop across exploratory research, planning, implementation commands, dogfood, verification, and judge. Persists one durable run in SQLite and emits per-stage receipts so the whole loop can be resumed…
- `run_self_heal` — Autonomous self-healing for detected drift issues. Fixes orphaned verification cycles
- `run_self_maintenance` — Run autonomous self-maintenance cycle. Checks TypeScript compilation, documentation sync, tool counts, test coverage, and more. Can auto-fix low-risk issues. Scope: quick (1hr check), standard (6hr), thorough (24hr analysis).
- `run_signal_sweep` — Run a live signal sweep across all data sources (HackerNews, GitHub Trending, Yahoo Finance, ProductHunt). Returns signals sorted by relevance with severity tiers (FLASH/PRIORITY/ROUTINE). Use this to find what
- `run_sync_bridge_flush` — Open the outbound websocket bridge, pair or resume the local device, and flush pending approved operations to the paired web account.
- `run_tests_cli` — Execute a shell test command with timeout, capture stdout/stderr, and return structured results. Useful for running test suites, linters, or build commands as part of verification workflows.
- `run_visual_qa_suite` — End-to-end visual QA pipeline: burst capture → SSIM stability analysis →
- `runNewsroomPipeline` — Trigger the full DRANE newsroom pipeline (Scout > Historian > Analyst > Publisher) for a given topic or entity. Returns the generated narrative analysis.
- `runSpotFixScan` — Scan for common operational issues: stale missions, blocked tasks with met deps, old sniff checks.
- `sandbox_batch` — Execute multiple commands, index all outputs, and run multiple search queries — all in ONE call. This is the highest-efficiency tool: one sandbox_batch replaces N sandbox_execute calls + M sandbox_search calls. Use for research phases, m…
- `sandbox_execute` — Run a shell command, automatically index the output into the sandbox, and return only a summary. The raw stdout/stderr stays in SQLite — only line counts and a preview enter context. Use instead of raw shell execution for commands that p…
- `scrapling_crawl` — Start a multi-page spider crawl with extraction. Crawls from start URLs, follows links matching a CSS selector, extracts data per page. Returns a session_id to poll with scrapling_crawl_status. Max 500 pages, 1-20 concurrent. Domain whit…
- `scrapling_crawl_stop` — Stop a running crawl session. Pass the session_id from scrapling_crawl. Items collected so far are preserved. Use when you have enough data or need to abort. Requires Scrapling bridge server.
- `self_implement` — Self-implement missing agent infrastructure. Generates implementation plan and code templates for: agent_loop, telemetry, evaluation, verification, multi_channel, self_learning, governance. Uses dry-run by default.
- `simulate_decision_paths` — Run Monte Carlo simulation for founder decisions. Generates multiple random paths to visualize possible future outcomes. Shows average payoff, success/failure rates, best/worst paths, and which decisions matter most. Use for: fundraising…
- `smart_select_tools` — LLM-powered tool selection: sends your task description + a compact tool catalog to a fast model (Gemini 3 Flash, GPT-5-mini, or Claude Haiku 4.5) to pick the best 5-10 tools. Much more accurate than keyword search for ambiguous queries …
- `spawn_openclaw_agent` — Start a secure OpenClaw session with safety rules applied.
- `start_autonomy_benchmark` — Start an autonomous capability benchmark. Defines a complex build challenge and tracks agent progress through milestones. Inspired by Anthropic\
- `start_dogfood_session` — Start a new dogfood session for one of the 3 canonical loops (weekly_reset, pre_delegation, company_search). Returns sessionId for subsequent recording.
- `start_eval_run` — Start a new eval run. Define the test batch upfront with test cases (input, intent, expected behavior), then record results as each case is executed. Rule: no change ships without an eval improvement.
- `start_execution_run` — Start a live Convex-backed execution trace run for a workflow. Creates a task session and trace together so later steps, decisions, evidence, verifications, and approvals all land on the same durable run.
- `start_ui_dive` — Initialize a UI/UX Full Dive session. Auto-launches a headless Playwright browser if installed (zero setup). Navigates to the app URL and optionally auto-discovers page components from the DOM. If Playwright is not installed, falls back …
- `start_verification_cycle` — Start a new 6-phase verification cycle for a non-trivial implementation. Returns the cycle ID and Phase 1 instructions. Call this before declaring any integration, migration, or protocol-level change done.
- `switchTab` — Switch between research hub tabs
- `thompson_pipeline` — End-to-end Thompson Protocol pipeline orchestrator. Takes a complex topic and runs it through all 4 agents (Writer → Feynman Editor → Visual Mapper → Anti-Elitism Linter) with quality gate. Returns the full execution plan with agent prom…
- `transcribe_audio_file` — Transcribe a local audio file (MP3/WAV/etc) to text using faster-whisper via Python. Deterministic, no network.
- `trigger_batch_run` — Run a scheduled task right now instead of waiting.
- `trigger_investigation` — When an eval run shows regression, trigger a new verification cycle to investigate. This is how the outer loop feeds the inner loop: regressions trigger 6-phase investigations.
- `triple_verify` — Run triple verification on agent implementation. V1: Internal codebase analysis. V2: External authoritative source validation (Anthropic, OpenAI, LangChain, etc.). V3: Synthesis with recommendations and source citations. Optionally gener…
- `validate_agent_compatibility` — Run the agent validation harness — simulates how AI agents (Claude Code,
- `analyze_experiment_data` — Analyze experiment data (CSV or JSON) and generate publication-ready analysis paragraphs. Uses \\paragraph{Conclusion} + analysis structure. Strict: all conclusions must be grounded in the provided data — no fabrication. Returns LaTeX or…
- `analyze_figma_flows` — Full Figma flow analysis pipeline: extract frames from Figma file (depth=3 tree traversal), cluster into flow groups via priority cascade (section > prototype > name-prefix > spatial), and generate overlay visualization. Returns FlowAnal…
- `analyze_repo` — Analyze a GitHub repository
- `analyze_screenshot` — Send a screenshot to a vision-capable AI model for analysis. Accepts base64 image data (from capture_ui_screenshot) and returns the model
- `analyze_seo_content` — Analyze HTML or text content for SEO quality: word count, sentence count, paragraph count, Flesch-Kincaid readability score, heading structure, keyword density (if targetKeyword provided), and internal vs external link ratio. Works on ra…
- `analyze_voice_config` — Validate a voice pipeline configuration. Checks STT/TTS/LLM compatibility, estimates per-minute costs, identifies the latency bottleneck, and suggests optimizations (streaming, caching, pre-generation). Knowledge-based analysis, no live …
- `ask_context` — Ask against saved NodeBench context first. This searches session memory and the accumulated knowledge base so repeated setup and rediscovery costs stop compounding.
- `assess_risk` — Assess risk tier for a given action. Returns tier (low/medium/high), reversibility, external impact, and recommendation (auto_approve/log_and_proceed/require_confirmation). Use before executing any non-trivial action.
- `audit_openclaw_skills` — Scan installed OpenClaw tools for security risks: dangerous patterns,
- `audit_workflow_definition` — Analyze an OpenClaw workflow configuration for reliability, security, and performance issues:
- `auditTelemetry` — Audit inference call telemetry for anomalies: cost spikes, latency outliers, zero-cost suspicious calls.
- `benchmark_voice_latency` — Calculate theoretical latency for one or more voice pipeline configurations. Breaks down STT, LLM (first token + completion), and TTS latency. Shows total and user-perceived latency (with streaming optimizations). Rates each config as ex…
- `build_claim_graph` — Extract claims from a source packet and link each claim to its evidence. Returns a directed graph of claims with supporting/contradicting evidence, confidence per claim, and whatWouldChangeMyMind for each.
- `build_diligence_packet` — Build a diligence-oriented export payload from the canonical company packet.
- `build_investor_packet` — Build an investor-oriented export payload from the canonical company packet.
- `burn_rate_sanity` — Sanity check founder burn against runway and stage expectations.
- `calculate_terminal_value` — Calculate terminal value using perpetuity growth or exit multiple method. Perpetuity method: TV = FCF(n+1) / (WACC - g) Exit multiple method: TV = Metric × Multiple Terminal value typically represents 60-80% of total enterprise value.
- `calculate_valuation` — Calculate final enterprise value and equity value. Calculation: 1. PV of forecast FCF (Years 1-5) 2. PV of terminal value 3. Enterprise Value = PV(FCF) + PV(TV) 4. Equity Value = EV - Net Debt 5. Implied Share Price = Equity Value / Shar…
- `calculate_wacc` — Calculate Weighted Average Cost of Capital (WACC) using CAPM. Components: - Risk-free rate (US 10Y Treasury) - Beta (from comparables or financial data) - Market risk premium - Cost of debt - Tax rate - Capital structure (debt/equity wei…
- `capture_responsive_suite` — Capture screenshots at all 3 standard responsive breakpoints (mobile 375px, tablet 768px, desktop 1280px) in one call. Returns all 3 screenshots as inline images that multimodal agents can see and compare side-by-side. Also captures cons…
- `cheapest_valid_path` — Return the cheapest valid workflow path for the stated objective.
- `check_agent_inbox` — Read unread messages for the current agent session. Filter by category, sender, or priority. Messages are marked as read after retrieval. Use this at the start of a session to pick up handoffs and blockers from other agents.
- `check_contract_compliance` — Analyze an agent session
- `check_design_compliance` — Check a single .tsx/.ts file for design governance compliance. Runs all banned pattern checks (color, typography, focus, button) plus structural checks for view files (nb-page-shell, empty state, loading state). Returns violations array …
- `check_dive_drivers` — Setup wizard for MCP automation drivers. Probes the system for Android SDK (ANDROID_HOME, adb, emulator), iOS tools (Xcode, go-ios, simulators), Playwright, and Node.js version. Returns a readiness report with per-area status (ready/part…
- `check_email_setup` — Diagnostic wizard for email tool configuration. Checks env vars (EMAIL_USER, EMAIL_PASS, etc.), optionally tests SMTP/IMAP connections, and returns step-by-step setup instructions for missing pieces. Supports Gmail, Outlook, Yahoo, and c…
- `check_framework_updates` — Get a structured checklist of sources to check for framework/SDK updates. Pre-built source lists for: anthropic, langchain, openai, google, mcp. Each source includes what to check for. Use this to guide your reconnaissance research syste…
- `check_git_compliance` — Validate branch state, uncommitted changes, and conventional commit compliance. Checks if on a protected branch, lists uncommitted changes, and optionally validates recent commit messages against conventional commit format (type(scope): …
- `check_mcp_setup` — Comprehensive diagnostic wizard for the entire NodeBench MCP. Checks all env vars, API keys, optional npm packages, and external services across every domain. Returns a full readiness report with per-domain status and step-by-step setup …
- `check_openclaw_setup` — Check if OpenClaw is ready to use: verifies the server is installed,
- `check_openclaw_status` — Check if OpenClaw is installed, Docker is available, and any sessions are active.
- `check_page_performance` — Lightweight page performance check via HTTP fetch (no browser). Measures: response time, content size, compression (content-encoding header), cache headers (cache-control, etag, last-modified), and HTTP status. Returns a performance scor…
- `check_paper_logic` — Check academic text for logical issues: contradictions between statements, undefined terms, terminology inconsistency, and Chinglish patterns. Uses a high-tolerance threshold — only flags issues that genuinely impede comprehension. Retur…
- `check_peer_messages` — Read the direct messages for a peer, optionally restricting to unread items.
- `check_plugin_update_readiness` — Check whether NodeBench MCP is ready for a version/update push across installer, plugin metadata, and editor surfaces.
- `check_skill_freshness` — Check if registered skills are stale by comparing current source file hashes
- `check_webmcp_setup` — Check WebMCP prerequisites: Playwright installation, Chromium browser availability, and any cached origin data. Returns setup instructions if anything is missing.
- `check_wordpress_site` — Detect whether a site runs WordPress and assess its security posture. Checks: WP generator meta tag, wp-content/wp-includes paths, WP REST API (/wp-json/), login page (/wp-login.php), XML-RPC (/xmlrpc.php), active theme, and visible plug…
- `claim_verification_scan` — Scan high-risk claims against available evidence classes.
- `classify_failure` — Classify a failure by canonical system layer taxonomy. Tracks symptom, root cause, and system layer for structured triage.
- `cluster_figma_flows` — Cluster Figma frames into flow groups using multi-signal priority cascade: 1) section-based grouping (highest priority), 2) prototype connection Union-Find, 3) name-prefix matching (e.g.
- `compare` — Compare 2-4 entities using the same report-shaped output. The tool backfills quick diligence packets first so the comparison result is usable immediately.
- `compare_eval_runs` — Compare two eval runs to decide whether a change should ship. Returns side-by-side scores and a deploy/revert recommendation. Rule: no change ships without an eval improvement.
- `compare_founder_directions` — Compare multiple founder directions side by side across strategic angles, issue count, confidence, and recommended wedge.
- `compare_options` — Generate a formatted side-by-side comparison table from scored research results. Takes either raw options or a score_id from multi_criteria_score. Outputs markdown table with normalized bars, rank badges, and decision explanation. Perfec…
- `compare_savings` — Compare token usage, time savings, and cost estimates. Optionally compare two sessions for before/after ROI. Shows total tool calls, tokens, estimated time saved, and cost.
- `compare_workflow_paths` — Compare current and optimized workflow paths and quantify likely savings.
- `compute_calibration` — Compute calibration bins and Brier aggregates across all resolved forecasts. Returns 10 bins (0-10%, 10-20%, ..., 90-100%) with predicted vs observed frequency.
- `compute_web_stability` — Compute frame-to-frame stability metrics for a burst capture. Calculates
- `connect_channels` — Connect to multiple information channels for aggressive information gathering. Channels: slack, telegram, discord, email, web, github, docs. Synthesizes findings across channels with source citations.
- `convex_analyze_components` — Analyze Convex component imports in convex.config.ts. Lists all installed Convex components (agent, workflow, rag, etc.), checks for unused imports, conditional loading, and configuration issues. Essential before adding new components to…
- `convex_analyze_http` — Analyze convex/http.ts for HTTP endpoint issues: duplicate routes, missing CORS headers, missing OPTIONS preflight handlers, missing httpRouter/httpAction imports, and missing default export. Returns route inventory with methods and paths.
- `convex_audit_actions` — Audit Convex actions for: ctx.db access (fatal — actions cannot access DB directly), missing
- `convex_audit_authorization` — Audit Convex functions for authorization issues: public mutations/actions writing to DB without auth checks, getUserIdentity() without null checks, sensitive-named functions without auth, and unprotected user data queries.
- `convex_audit_data_modeling` — Audit Convex schema for data modeling issues: deeply nested objects (flatten into tables), dangling v.id() references to non-existent tables, tables approaching field count limits, v.any() overuse, and array fields that may hit size limits.
- `convex_audit_dev_setup` — Audit Convex project development setup: .gitignore includes _generated/, .env.example exists, convex.json is valid, convex is in dependencies, TypeScript strict mode, project initialization status.
- `convex_audit_diff` — Compare the latest audit run against the previous run to show new issues, fixed issues, and trend direction (improving/stable/degrading). Like SonarQube
- `convex_audit_functions` — Audit all exported Convex functions for: missing validators (args/returns), old syntax usage, sensitive functions exposed publicly, and action-from-action anti-patterns. Scans all .ts files in the convex/ directory.
- `convex_audit_pagination` — Audit Convex pagination patterns: missing paginationOptsValidator in query args, unbounded numItems (DoS risk), and .paginate() usage inventory.
- `convex_audit_query_efficiency` — Audit Convex queries for efficiency issues: .collect() without limits (unbounded reads), .filter() without indexes (full table scans), mutations used for pure reads (losing reactivity), and .first() vs .unique() misuse.
- `convex_audit_schedulers` — Audit Convex scheduled function usage (ctx.scheduler.runAfter/runAt): detects infinite self-scheduling loops, sub-second delays without backoff, scheduler calls in queries (impossible), unprotected scheduler calls in actions, and excessi…
- `convex_audit_schema` — Analyze a Convex project
- `convex_audit_storage_usage` — Audit Convex file storage usage: missing null checks on ctx.storage.get()/getUrl(), storage IDs stored as v.string() instead of v.id(
- `convex_audit_vector_search` — Audit Convex vector search implementation: validates vectorIndex dimensions against known embedding models, checks for missing filterFields, v.array(v.float64()) usage, dimension mismatches between schema and code, and undefined index re…
- `convex_bootstrap_project` — Scan a Convex project directory and generate a comprehensive health report. Checks: schema presence, function count, validator coverage, index usage, env vars, auth setup, and known gotchas. Returns a prioritized improvement plan.
- `convex_check_crons` — Validate cron job definitions in convex/crons.ts. Checks: handler references use internal (not api), no duplicate names, schedule validity, frequency analysis. Returns cron inventory with issues.
- `convex_check_env_vars` — Check that all environment variables referenced in Convex code (process.env.*) are defined in .env files. Identifies missing vars and suggests where to set them.
- `convex_check_function_refs` — Validate function references across the Convex codebase. Checks that ctx.runQuery/runMutation/runAction use proper api.x.y or internal.x.y references (not direct function passing). Flags potential broken references.
- `convex_check_type_safety` — Check Convex code for type safety issues:
- `convex_check_validator_coverage` — Check that all exported Convex functions (query, mutation, action, and their internal variants) have both args and returns validators. Reports functions missing validators and those using deprecated old syntax.
- `convex_critter_check` — The accountability partner that wants to know everything — answer
- `convex_discover_tools` — Search for available convex-mcp-nodebench tools by keyword, category, or task description. Returns matching tools with descriptions and quickRefs to guide your next action.
- `convex_export_sarif` — Export stored audit results as SARIF 2.1.0 JSON. SARIF is the industry standard for static analysis results — integrates with GitHub Code Scanning, VS Code Problems panel, and CI pipelines. Outputs file:line locations, severity levels, a…
- `convex_get_methodology` — Get step-by-step guidance for Convex development workflows. Topics: overview, convex_schema_audit, convex_function_compliance, convex_deploy_verification, convex_knowledge_management, convex_index_optimization. Call with
- `convex_scan_capabilities` — Analyze Convex source files for structural patterns. Scans a single file or entire convex/ directory and returns a capability report: function types (queries, mutations, actions, crons, http), schema constructs (tables, indexes, validato…
- `convex_search_gotchas` — Search the persistent Convex gotcha database using full-text search. Returns relevant gotchas, edge cases, and patterns. Always search before starting a new Convex implementation to avoid known pitfalls.
- `convex_snapshot_schema` — Capture a snapshot of the current schema.ts for later diffing. Stores table names, schema size, and timestamp. Use before and after schema changes to track what changed.
- `convex_suggest_indexes` — Analyze query patterns across all Convex functions and suggest missing indexes. Scans for .query().filter() patterns and compares against defined indexes in schema.ts.
- `convex_verify_concept` — Check if Convex source files contain all required code signatures for a concept. Provide a concept name (e.g.,
- `critter_check` — The accountability partner that wants to know everything — answer
- `crypto_price_historical` — Get historical daily price data for a cryptocurrency. Optionally filter by date range.
- `crypto_price_quote` — Get the latest cryptocurrency price quote. Accepts symbols like BTC, ETH, or BTC-USD.
- `csv_aggregate` — Aggregate values from a local CSV (count/sum/avg/min/max) with optional filters. Deterministic, no network.
- `csv_select_rows` — Select rows from a local CSV using deterministic filters. Returns bounded results (selected columns + matching rows). No network.
- `decision_quality_scan` — Check whether the founder decision has clear criteria, falsifiers, and next actions.
- `deeptrace_check_permission` — Pre-flight permission check — can this agent use this tool? Resolves the agent
- `deeptrace_get_evidence_pack` — Retrieve an evidence pack by ID, including all its constituent chunks with full content and provenance metadata.
- `deeptrace_get_passport` — Retrieve an agent
- `deeptrace_list_receipts` — List action receipts with optional filtering by agent, policy action, or tool. Returns receipts sorted by creation time (newest first).
- `deeptrace_receipt_stats` — Get aggregate statistics across all receipts — total count, policy action breakdown, top agents, and top tools.
- `deeptrace_search_evidence` — Full-text search across ingested evidence chunks. Returns matching chunks with relevance ranking, source URLs, and content hashes for provenance verification.
- `deeptrace_verify_receipt` — Verify a receipt
- `delta_brief` — Generate a
- `delta_compare` — Side-by-side entity comparison. Produces a delta.diligence comparison packet highlighting differences, strengths, and weaknesses across 2-4 entities.
- `delta_diligence` — Deep entity intelligence teardown. Produces a delta.diligence packet with signals, risks, opportunities, and evidence for any company or entity. Use for competitive analysis, investment diligence, or market research.
- `delta_packets` — List recent delta packets. View your packet history, filter by type, and track lineage.
- `delta_review` — Reconcile a forecast or recommendation against reality. Produces a delta.review packet so the next decision uses outcomes instead of memory drift.
- `delta_scan` — Run a self-diligence market coverage scan. Produces a delta.market packet analyzing what NodeBench Delta covers well, what gaps exist, and what competitors are doing. The product eats its own dogfood.
- `delta_watch` — Add, remove, or list entities on your watchlist. Watched entities are checked for material changes during delta_brief runs. Use to monitor competitors, partners, or market segments.
- `design_voice_pipeline` — Given requirements (latency, privacy, platform, budget), recommend an optimal STT/TTS/LLM stack. Returns top 3 configurations ranked by fit, with estimated round-trip latency, monthly cost, and architecture notes. Knowledge-based — no li…
- `detect_company_mode` — Classify a request as own-company, external-company, or mixed-comparison mode before packet routing.
- `detect_contradictions` — Detect contradictions across multiple sources for an entity.
- `detect_repeated_questions` — Analyze causal_events to find patterns where the user/agent asks the same strategic question repeatedly. Uses Jaccard similarity on summary text to cluster repeated queries.
- `detect_subvertical` — Detect the founder subvertical from the query and context.
- `detect_temporal_signal` — Analyze observations in a stream and detect temporal signals: momentum (sustained directional trend), regime_shift (rolling mean shift), anomaly (z-score outlier), causal_hint, opportunity_window, or risk_window. Returns detected signals…
- `detect_vertical` — Detect the founder vertical and subvertical from the query and context.
- `diff_crawl` — Before/after site comparison. First call captures baseline. Second call diffs against baseline. Shows added/removed/changed pages.
- `diff_outputs` — Compare two text or JSON outputs and produce a structured diff with similarity score. Use for model comparison, oracle validation, before/after analysis, or regression detection. Returns added/removed/changed elements with a human-readab…
- `diff_screenshots` — Compare two images structurally using pixel-level analysis. Computes perceptual similarity, difference regions, and visual summary. Requires sharp. Useful for visual regression testing, UI QA, and screenshot comparison.
- `discover_infrastructure` — Discover existing agent infrastructure in the codebase. Scans for agent loops, telemetry, evaluation, verification, multi-channel integrations, self-learning systems, and governance patterns. Returns what exists, what
- `discover_tools` — Multi-modal tool search engine with 14 scoring strategies: keyword, fuzzy (typo-tolerant), n-gram (partial words), prefix, semantic (synonym expansion), TF-IDF (rare tags score higher), regex, bigram (phrase matching), domain cluster boo…
- `discover_vision_env` — Discover available vision-capable AI SDKs and API keys in the current environment. Returns which providers can be used for screenshot analysis. Call this before analyze_screenshot to know what
- `distribution_surface_scan` — Scan which distribution surfaces are actually ready right now.
- `dive_code_locate` — Find the exact source code location for a bug, component, or design issue. Uses grep/ripgrep to search the project codebase for the relevant code. Maps UI bugs to file:line so you know exactly where to fix. Stores the location in the DB …
- `dive_code_review` — Generate a structured code review report from all dive findings — similar to CodeRabbit or Augment Code Review. Aggregates bugs, design issues, interaction test failures, console errors, missing components, and backend link gaps into a p…
- `dive_preflight` — Analyze a project BEFORE starting a UI dive. Scans the project directory to detect: framework (Vite, Next.js, CRA, etc.), dev scripts, required services (frontend, backend like Convex/Supabase/Firebase), port assignments, whether service…
- `dive_snapshot` — Capture a screenshot or accessibility snapshot of the current page during a dive session. Requires the built-in Playwright browser to be active (launched by start_ui_dive). Returns the screenshot as an inline image for multimodal agents,…
- `dive_walkthrough` — Generate a comprehensive page-by-page, component-by-component walkthrough document for a dive session. Includes: route map with source files, component tree, interaction test results with pass/fail per step, screenshots referenced at eac…
- `economy_gdp` — Get the latest GDP data for a country from the World Bank. Defaults to the US.
- `economy_inflation` — Get the latest consumer price inflation rate (CPI) for a country from the World Bank. Defaults to the US.
- `enrich_entity` — Enrich an entity (company, person, theme, market) with structured intelligence.
- `enrich_recon` — Retroactively enrich an existing recon session with live web search results. Call this after run_recon when you
- `entity_lookup` — Quick intelligence on any company, person, or topic. Type a name, get structured facts, signals, and suggested next tools. The simplest entry point into NodeBench — no setup needed.
- `equity_fundamental_overview` — Get a fundamental overview for an equity ticker including price, sector, industry, P/E ratios, market cap, and other key metrics.
- `equity_price_historical` — Get historical daily OHLCV price data for a given equity ticker. Optionally filter by start/end date (YYYY-MM-DD).
- `equity_price_quote` — Get the latest equity/stock price quote for a given ticker symbol. Tries Stooq first, then Yahoo Finance as fallback.
- `evidence_gap_scan` — List missing evidence classes and materials for diligence readiness.
- `export_audit_report` — Export a session activity log as formatted markdown for pull request reports,
- `export_crunchbase_profile` — Export a Crunchbase-like structured profile from the company packet.
- `export_dimension_bundle` — Export the full DeepTrace dimension bundle for an entity: latest profile, snapshots, evidence, and interaction effects in one response.
- `export_pitchbook_profile` — Export a PitchBook-like structured profile from the company packet.
- `export_yc_application_context` — Export YC-style application context from the company packet.
- `exportDocumentToMarkdown` — Export a document to Markdown format. Returns { title, markdown }.
- `extract_figma_frames` — Extract all frames from a Figma file using depth=3 tree traversal (DOCUMENT -> CANVAS -> SECTION -> FRAME). CRITICAL: uses depth=3 not depth=2 — depth=2 only gets SECTION nodes, missing the FRAME nodes inside them. Returns structured Fig…
- `extract_fractions_and_simplify_from_image` — Extract slash-style fractions (e.g. 3/4) from body text in an image and also detect stacked numerator/denominator fractions in a worksheet-style region, returning the simplified answers. Deterministic, no network.
- `extract_patent_claims` — Extract likely patent and IP claims from source text.
- `extract_publication_metadata` — Extract publication-oriented metadata from source text.
- `extract_regulatory_artifacts` — Extract regulatory path signals from source text.
- `extract_structured_data` — Extract structured JSON data from unstructured text using an LLM. Provide the text and a description of the fields you want extracted. Returns validated JSON matching your schema. Useful for turning research findings, web pages, or docum…
- `extract_trial_evidence` — Extract trial, study, or lab evidence snippets from source text.
- `extract_variables` — Identify and weight the key variables driving an entity
- `fetch_rss_feeds` — Fetch and parse all registered RSS/Atom feeds (or specific URLs). New articles are stored in SQLite with is_new=1 for digest generation. Previously seen articles (same source_url + link) are skipped. Returns per-feed counts and articles.
- `fetch_url` — Fetch a URL and extract its content as markdown, text, or raw HTML. Useful for reading documentation, blog posts, API references, and web pages. Uses linkedom for HTML parsing when available, with fallback to basic text extraction.
- `financial_hygiene_check` — Return the hidden financial hygiene requirements many founders forget before diligence.
- `find_contradictions_for` — Find all entities that contradict a given entity or concept.
- `findTools` — Search available tools by keyword or capability description. Returns matching tool names and descriptions ranked by BM25 relevance. Use this to discover which tools are available for a task.
- `forecast_temporal_trend` — Zero-shot forecasting on numeric time series. Supports naive (last value), linear (regression), and exponential_smoothing methods. Returns predictions with confidence intervals. Placeholder for future TSFM (Chronos/TimesFM) microservice …
- `founder_company_naming_pack` — Generate a founder company naming shortlist and starter profile.
- `founder_deep_context_gather` — MUST be called before generating or updating a Founder Artifact Packet.
- `founder_delegation_boundary_scan` — Separate delegable work from founder-only work for the current direction.
- `founder_direction_assessment` — Pressure-test a founder direction against team shape, AI stance, build speed,
- `founder_gaps_detect` — Detect missing foundations, hidden risks, and weak strategic angles for a founder direction.
- `founder_local_gather` — Gathers all locally-available context for a founder packet: git log,
- `founder_materials_check` — Return the founder materials checklist and missing external-readiness artifacts.
- `founder_next_unlocks` — List the next progression unlocks required to move the founder to the next stage.
- `founder_ontrack_scorecard` — Return explicit 2-week and 3-month on-track or off-track scorecards.
- `founder_packet_diff` — Compares two Founder Artifact Packets and returns a structured diff showing
- `founder_packet_history_diff` — Compares the most recent Founder Artifact Packet for an entity against
- `founder_packet_validate` — Validates a draft Founder Artifact Packet against quality gates before saving.
- `founder_readiness_score` — Return the founder readiness score and a concise interpretation.
- `founder_stage_assess` — Return the founder progression stage, readiness score, and stage ladder for the current direction.
- `founder_target_customer_map` — Map the downstream customer groups the company should target first.
- `fusionSearch` — Multi-source fusion search with reranking. Modes: fast (single source), balanced (2-3 sources), comprehensive (all sources with reranking).
- `generate_countermodels` — For every main thesis or scenario, generate serious alternative explanations with their own evidence and confidence. Forces intellectual honesty by surfacing counter-arguments and what would validate each.
- `generate_summary` — Generate AI-powered summary and insights from completed DCF model. Provides: - Key valuation metrics - Investment thesis (why this valuation makes sense) - Risk factors (4-5 key risks) - Sensitivity analysis (impact of assumption changes…
- `get_ab_test_report` — Generate an A/B test comparison report for static vs dynamic toolset loading. Shows session counts, tool counts, load events, error rates, and per-toolset load frequency. Use after running sessions in both modes to evaluate the impact of…
- `get_active_forecasts` — List active forecasts. Optionally filter by those needing refresh (based on last refresh time and frequency).
- `get_agent_role` — Get the current agent
- `get_annual_retrospective` — Full year view: quarterly summaries, yearly milestones, category distribution, growth metrics.
- `get_autopilot_status` — Check the status of scheduled tasks: when the last run happened,
- `get_batch_run_history` — See the history of past scheduled runs: what was found,
- `get_benchmark_history` — View historical benchmark batch results. Shows RCA and PRR trends over time.
- `get_benchmark_oracles` — Return the oracle definitions for founder autonomy and workflow optimization benchmark lanes.
- `get_benchmark_report` — Get the full detailed report for a specific benchmark batch by batchId.
- `get_boilerplate_status` — Check what NodeBench infrastructure is already set up in a project vs what
- `get_causal_chain` — Trace the causality chain from a given event backwards through causedByEventId links. Returns the chain of events that led to this one.
- `get_compaction_recovery` — Recovery tool for post-context-compaction state restoration. Call this RIGHT AFTER Claude Code compacts context to recover session state, active intents, packet status, unresolved changes, and pending alerts. Returns a ready-to-use injec…
- `get_company_truth` — Get current canonical company truth from subconscious memory blocks.
- `get_context_bundle` — Returns the full NodeBench context bundle: pinned identity (mission, wedge, confidence),
- `get_daily_brief_summary` — Get the latest daily brief summary from local SQLite. Returns dashboard metrics, features, and source summary. No network needed — reads cached data.
- `get_daily_log` — Get all tracked actions for a specific date, grouped by session with milestone highlights.
- `get_design_spec` — Return the full design governance specification as structured JSON. Includes: approved semantic colors, typography classes and uppercase policy, component layout primitives, spacing scale, button classes, focus ring pattern, motion rules…
- `get_design_violations` — Scan the entire src/ directory for design governance violations. Groups results by file, sorted by severity. Supports filtering by severity (high/medium/low/all) and category (color/typography/layout/states/focus/button/all). Returns sum…
- `get_dimension_profile` — Fetch the latest persisted DeepTrace dimension profile, including regime label, policy context, confidence, and the normalized dimension state.
- `get_distribution_surfaces` — Inspect NodeBench MCP distribution surfaces: npm/npx, installer, plugin configs, Smithery, and shared web review surfaces.
- `get_dive_report` — Generate a comprehensive UI/UX Full Dive report for a session. Includes: executive summary, component tree, all bugs grouped by severity, per-component interaction traces, Mermaid diagram, and actionable recommendations. Optionally marks…
- `get_dive_tree` — Get the full XML-like component tree for a dive session. Shows all registered components in their hierarchy with status, agent assignments, interaction counts, and bug counts. Also returns a Mermaid diagram for visual rendering. Use this…
- `get_dogfood_sessions` — List recent dogfood sessions with their judge scores. Filter by loop type.
- `get_dogfood_telemetry` — Query dogfood telemetry rows with optional filters. Returns matching rows plus computed averages (tool calls, latency, cost, judge score).
- `get_drift_report` — Detect configuration and state drift in the NodeBench system. Checks for orphaned verification
- `get_engine_context_health` — Returns accumulated knowledge health: learnings count + freshness, conformance trend direction (improving/stable/regressing), recent run scores, content archive size, and workflow coverage. Use to understand how much context the engine h…
- `get_entity_graph_summary` — Get a summary of the knowledge graph: entity counts by type, edge counts by relation, recent additions.
- `get_event_ledger` — Query the causal event ledger with optional filtering by entityId, eventType, entityType, or correlationId.
- `get_failure_triage` — Get open failure cases grouped by system layer with frequency counts. The triage board for fixing system gaps.
- `get_figma_design_context` — Get design context for a specific component or screen from the codebase governance spec. Returns the relevant design tokens, typography rules, spacing rules, and component patterns that apply. Use this to understand what a component SHOU…
- `get_flywheel_status` — Get the current state of both loops (Verification inner loop and Eval outer loop) and how they connect. Shows active verification cycles, recent eval trends, and cross-loop connections.
- `get_forecast_chain` — Get full audit trail for a forecast: the forecast itself, all evidence entries, update history, and resolution (if resolved). Complete chain of custody.
- `get_forecast_evidence` — Query evidence ledger for a forecast. Optionally filter by signal direction (supporting/disconfirming/neutral).
- `get_forecast_track_record` — Get aggregate Brier scores, calibration summary, and track record statistics across all resolved forecasts.
- `get_founder_execution_order` — Return the canonical founder/company packet execution order so all surfaces follow the same run sequence.
- `get_founder_job_topology` — Return the queue and job topology for founder ingestion, sweeps, deltas, packet refresh, exports, delegation, and benchmarks.
- `get_founder_packet_resource` — Fetch the resource URI, pull query, and subscription query for a founder issue or resolution packet.
- `get_founder_progression_rubric` — Return the explicit founder progression rubric, including mandatory and optional signals for each stage.
- `get_gate_history` — Get the history of quality gate runs for a given gate name. Shows pass/fail trend over time.
- `get_gate_preset` — Get the rules for a built-in quality gate preset. Returns rule names, descriptions, and evaluation instructions so you can check each one. Presets: engagement (content quality), code_review (implementation quality), deploy_readiness (pre…
- `get_important_changes` — Query flagged important changes with optional status filtering. Returns changes ordered by timestamp descending.
- `get_improvement_recommendations` — Analyze all persisted data and return actionable improvement recommendations. Detects: unused tools, missing quality gates, unresolved gaps, knowledge gaps, underutilized phases, and tool error patterns. The self-reinforced learning engine.
- `get_ingest_status` — Report which data sources are available for ingestion. Checks if Claude Code transcripts exist, what project directories are accessible, and overall sync readiness.
- `get_judge_history` — Get the history of LLM judge runs, optionally filtered by scenario.
- `get_latest_signals` — Get the most recent signal sweep results without running a new sweep. Returns cached signals from the last sweep. Fast — no API calls.
- `get_messaging_health` — Check which messaging channels are working.
- `get_monthly_report` — Monthly rollup of actions: weekly breakdown, trending categories, velocity (actions/day), milestone timeline.
- `get_narrative_status` — Get narrative thread status from local SQLite. Returns threads grouped by phase (emerging, escalating, climax, resolution, dormant) with event counts. No network needed.
- `get_observability_summary` — Unified observability summary combining MCP system pulse, sentinel probes, watchdog status,
- `get_openclaw_audit` — View the activity log for OpenClaw sessions. Shows every skill call
- `get_openclaw_delivery_status` — Check if your messages were delivered.
- `get_openclaw_results` — Get results and safety summary for an OpenClaw session.
- `get_ops_dashboard` — Get operational dashboard status from local SQLite. Returns last sync info, tool call frequency, active verification cycles, and data counts. No network needed.
- `get_packet_lineage` — Trace the full derivation chain for a packet or entity.
- `get_parallel_status` — Get a comprehensive overview of all parallel agent activity: active task claims, role assignments, context budget status, and recent oracle comparison results. Essential for new agent sessions to orient themselves (Anthropic pattern:
- `get_policy_detail` — View full details of a sandbox policy including effective allowlist/blocklist after merging defaults.
- `get_proactive_alerts` — Scan causal memory for watchlist-worthy alerts: new events on tracked entities, unresolved important changes, stale packets, trajectory drift, and repeated unanswered queries. Returns prioritized alerts with suggested actions.
- `get_project_context` — Retrieve the stored project context (tech stack, architecture, conventions, etc.) and knowledge base stats. Call this at the start of any session to refresh your project awareness. If no project context exists, returns onboarding instruc…
- `get_quarterly_review` — Quarterly strategic view: monthly trends, category shifts, biggest milestones, velocity curve.
- `get_recon_summary` — Get aggregated summary of all findings from a recon session. Groups findings by category (breaking changes, new features, codebase patterns, etc.) with prioritized action items.
- `get_regression_gate` — Check if the 3 canonical loops pass. Returns per-loop scores, overall pass/fail, and regression detection.
- `get_repeat_cognition_metrics` — The key compound metric. Measures repeat question rate, manual reconstruction count, packet abandonment rate, delegation-without-restatement rate, and average time-to-useful-output.
- `get_role_packet_defaults` — Return the default packet, artifact, monitor, and delegation policy for a specific public role lens.
- `get_self_directed_delivery_run` — Load a previously recorded autonomous delivery run with all stage receipts, summaries, and final recommendations.
- `get_self_eval_report` — Generate a comprehensive self-evaluation report by cross-referencing all persisted data: verification cycles, eval runs, quality gates, gaps, learnings, recon sessions, and tool call trajectories. Identifies strengths, weaknesses, and ar…
- `get_sentinel_report` — Get the latest sentinel self-test report with all 9 probe results (build, e2e, design, dogfood,
- `get_session_compliance` — Score an OpenClaw session against its security policy.
- `get_session_journal` — Get all tracked actions from the current or a specified session, in chronological order.
- `get_session_profile` — Get the efficiency profile for the current session. Shows total calls, cost, latency, redundancy, and optimization suggestions.
- `get_shared_context_packet` — Fetch one shared-context packet directly and include the suggested resource URI plus pull/subscription filters for agent clients.
- `get_shared_context_peer` — Fetch one peer and its current summary, capabilities, and scopes.
- `get_shared_context_snapshot` — Inspect the current shared-context protocol state: peers, packets, handoffs, messages, and aggregate counts.
- `get_signal_recommendations` — Get founder-specific actionable recommendations from the latest signals. Each recommendation includes: what to do, why, and urgency (act_now / this_week / monitor).
- `get_skill_risk_profile` — Get the safety assessment for one or more OpenClaw skills:
- `get_source_trust_policy` — Return the source-level permission and trust policy for storage, summarization, and export across private and public source types.
- `get_state_diff_history` — Get the change history for a specific entity, showing all recorded state diffs in reverse chronological order.
- `get_subconscious_hint` — Get the subconscious
- `get_sync_bridge_status` — Inspect whether the device is local-only, connected but idle, or actively ready to sync to a paired web account.
- `get_system_pulse` — Get a real-time health snapshot of the NodeBench MCP system. Returns database status,
- `get_tool_graph` — Returns a JSON graph of tool relationships that grows with usage.
- `get_tool_quick_ref` — Get the quick reference for a specific tool: what to do next, related tools, methodology, and tips. Call this after using any tool to understand the recommended next step in the workflow.
- `get_trajectory_analysis` — Analyze tool usage trajectories across sessions. Returns tool frequency, error rates, average duration, phase distribution, and sequential patterns. Use this to understand how tools are actually being used and identify bottlenecks.
- `get_trajectory_summary` — Compute a trajectory summary for a date range: event counts by type, diff counts by change type, path step counts, and top affected entities.
- `get_traversal_plan` — Generate a traversal plan for accomplishing a goal across multiple views.
- `get_uptime_stats` — Get session uptime, tool call rates, error trends, and top tools over multiple time windows
- `get_usage_insights` — Get aggregate usage insights across all sessions. Shows top tools, repeated queries, cost breakdown, and optimization opportunities. This is the founder operating intelligence layer.
- `get_verification_status` — Get the current status of a verification cycle including all phases, gaps, and test results. Use this to understand where you are in the process and what to do next.
- `get_view_capabilities` — Get full capabilities for a specific view — actions, data endpoints,
- `get_view_state` — Get the current agent traversal session state — which view you
- `get_watchdog_log` — Get recent watchdog check results. Shows health score trend, detected issues, and auto-healed
- `get_weekly_summary` — Summarize a week
- `get_workflow_chain` — Get a recommended tool sequence for a common workflow. Returns step-by-step tool chain with actions for each step across feature dev, debugging, security, deployment, research, academic writing, CI/CD, multi-agent coordination, content p…
- `get_workflow_history` — Returns past runs for a specific workflow with scores, grades, step counts, and durations. Use to track conformance improvements over time and identify regression patterns.
- `getArtifactsWithHealth` — Get source artifacts annotated with verification health status. Shows which sources are verified, stale, or contradicted.
- `getCalibrationStats` — Get calibration statistics for the verification pipeline, including accuracy, F1 scores, and inter-annotator agreement.
- `getCanaryRegressions` — Get recent canary runs that detected regressions.
- `getCanaryTrend` — Get canary benchmark trend: throughput score, quality score, verdict, and delta over time.
- `getComparisonTrend` — Get baseline comparison trend for a benchmark family (investigation, canary, etc.).
- `getContradictoryPosts` — Get posts that contradict each other across threads, useful for fact-checking and dispute resolution.
- `getDealFlow` — Get the current deal flow pipeline with funding events, company data, and investment signals.
- `getDocument` — Get a document by ID, including title, content, metadata, and file info.
- `getEntity` — Get a canonical entity by its entityKey.
- `getEntityContext` — Get full entity context by ID, including all tracked metadata, relationships, funding data, and activity history.
- `getEntityContextByName` — Look up an entity context by its canonical name (exact match).
- `getEntityContextStats` — Get aggregate statistics about the knowledge base: total entities, entities by type, coverage metrics.
- `getEntityInsights` — Get deep entity insights for a company or person, including funding, key people, product pipeline, and persona-specific hooks (banker, VC, CTO, founder).
- `getEntityNetwork` — Get the full network graph for an entity: aliases, holdings, people, investors, and related entities.
- `getEvolutionDashboard` — Get the evolution dashboard: latest canary, pending routing recommendations, recent comparisons, and error summary.
- `getFactById` — Get a single fact by ID with its full context: source, extracted claim, linked artifacts, and verification status.
- `getFactsByRun` — Get all extracted facts from a specific verification run (e.g., from a daily brief or narrative pipeline run).
- `getFastestGrowingRepos` — Get fastest-growing GitHub repositories by star velocity over the past week.
- `getFolderWithDocuments` — Get a folder and all documents inside it.
- `getForYouFeed` — Get the personalized For You feed with ranked research items, funding events, and industry signals. Returns verification-tagged items grouped by date.
- `getHoldings` — Get all fund holdings for a given investor entity.
- `getHygieneReport` — Get post-execution hygiene report: stale missions, pending sniff checks, error rates.
- `getInvestorProfile` — Get investor profile with type, AUM, focus sectors, portfolio size.
- `getKnowledgeGraph` — Get a knowledge graph by source document, including nodes, edges, and claims.
- `getKnowledgeGraphClaims` — Get all claims extracted from a knowledge graph, useful for fact-checking and verification.
- `getLatestDashboard` — Get the latest research dashboard snapshot with metrics on deal flow, entity coverage, verification health, and model costs.
- `getLatestPublicDossier` — Get the latest public company/industry dossier with competitive analysis and market positioning.
- `getMethodology` — Get step-by-step guidance for a development methodology. Topics: verification, eval, flywheel, mandatory_flywheel, reconnaissance, quality_gates, ui_ux_qa, flywheel_ui_dogfood, agentic_vision, closed_loop, learnings, project_ideation, te…
- `getMigrationStats` — Get model migration statistics for chat threads and messages.
- `getMission` — Get a specific mission by its Convex ID.
- `getMissionByKey` — Look up a mission by its unique missionKey string.
- `getMissionDashboard` — Get the mission control dashboard: active missions, judging queue, sniff checks, and recent completions.
- `getModelCostSummary` — Get cost, token, latency, and error summary for a specific model over N days.
- `getOpenDisputes` — Get all open disputes (contradictions, contested facts) that need resolution across the narrative engine.
- `getPendingRoutingRecommendations` — Get pending model routing recommendations from the eval engine.
- `getPendingSniffChecks` — Get all pending human-in-the-loop sniff checks awaiting review.
- `getPersonProfile` — Get executive/person profile with employment history, board roles, and credibility score.
- `getPlan` — Retrieve a task plan by ID
- `getPublicThreads` — List all public narrative threads. Each thread tracks an evolving story across entities over time (e.g.,
- `getSignalTimeseries` — Get time-series signal data for research metrics like funding volume, entity mentions, or verification health over time.
- `getSloMetricsSummary` — Get SLO metrics for verification pipeline performance: latency percentiles, throughput, error rates.
- `getSourceRegistry` — Get the source registry for a domain, showing all tracked data sources with freshness and reliability scores.
- `getSpreadsheetRange` — Get cells within a range from a spreadsheet (row/col coordinates).
- `getStakeholderGraph` — Get the stakeholder analysis graph: actors, goals, fears, incentives, and incentive interpretations.
- `getTasksForMission` — Get all task plans for a mission, showing execution status, dependencies, and assigned agents.
- `getThread` — Get a single narrative thread by ID, including metadata, entity associations, and event count.
- `getThreadPosts` — Get posts (analyst notes, thesis updates, evidence) within a narrative thread.
- `getThreadsByEntity` — Get all narrative threads associated with a specific entity (company or person name).
- `getThreadStats` — Get aggregate statistics about the narrative engine: total threads, events, posts, disputes, and activity over time.
- `getThreadsWithEvents` — Get narrative threads with their recent events inlined, useful for getting a quick overview of active stories.
- `getTrendingRepos` — Get trending GitHub repositories tracked by NodeBench AI, sorted by growth velocity.
- `getVerificationsForFact` — Get all verification attempts for a specific fact, including source citations, verdicts, and confidence scores.
- `getVerificationSummary` — Get a summary of verification health across all tracked facts. Returns counts by verdict (VERIFIED, CORROBORATED, UNVERIFIED, CONTRADICTED, OUTDATED, INSUFFICIENT) and overall trust score.
- `grade_agent_run` — Grade a single agent run on both outcome quality (task success, regressions, time) and process quality (recon, risk, tests, gates, learnings). Combines deterministic grading from the task bank
- `grade_fraction_quiz_from_image` — Grade a fraction quiz shown in an image by OCRing the problems + student answers, computing correct answers, and scoring by problem type. Deterministic, no network.
- `graphify_report` — Get the GRAPH_REPORT.md analysis from a graphify run. Contains god nodes (most connected),
- `graphify_status` — Check if graphify is installed and ready. Returns version, installation instructions if missing.
- `heartbeat_shared_context_peer` — Refresh peer liveness and optionally publish a compact machine-readable summary of its current work.
- `hiring_gap_scan` — Identify the most obvious missing hiring lane for the current founder direction.
- `ingest_claude_code_sessions` — Scan Claude Code JSONL transcripts from ~/.claude/projects/. Returns session summaries with turn counts, token usage, timestamps, and working directories. Use to understand what the founder has been working on across Claude Code sessions.
- `ingest_codebase_changes` — Fingerprint key files in a directory (package.json, README, schema, CLAUDE.md, etc.) and detect what changed since last check. Use to track codebase evolution as founder context.
- `inject_context_into_prompt` — Wraps a user prompt with NodeBench
- `inspect_topology_shape` — Inspect the persisted Convex topology shape for the Reports graph. Use this after search_memory/search_report_context when deciding whether to expand a dense Mapper cluster, inspect an outlier, or reuse first-ring graph context before li…
- `invalidate_shared_context` — Invalidate a packet when it becomes stale, contradicted, or superseded.
- `investigate` — Investigate a company, person, or topic and return a concise sourced artifact. This is the default v3 entry point: one ask in, one report-shaped output out.
- `json_select` — Select a sub-value from a local JSON file using a JSON Pointer (RFC 6901) and return a bounded preview. Deterministic, no network.
- `judge_verify_subtask` — Judge verifies a subtask
- `list_agent_tasks` — List all current task claims across parallel agents. Shows who is working on what, blocked tasks, and recently completed work. Essential for new agent sessions to orient themselves and avoid duplicate work.
- `list_available_toolsets` — List all available toolsets showing which are currently loaded and which can be dynamically added. Includes tool counts and descriptions for each toolset.
- `list_available_views` — List all available views in the NodeBench AI frontend with titles,
- `list_contradictions` — List all open contradictions between memory blocks and graph entities.
- `list_dimension_evidence` — List the durable evidence rows behind a DeepTrace dimension profile. Useful for auditing why a score or availability status was assigned.
- `list_dimension_interactions` — List stored interaction effects for an entity, such as capital plus investor quality reducing execution fragility or narrative outpacing evidence.
- `list_dimension_snapshots` — List historical DeepTrace dimension snapshots for an entity to inspect regime transitions over time.
- `list_driver_tools` — List all tools available from connected MCP drivers. Shows tool names, descriptions, and input schemas. Use this to discover what a connected driver can do before calling its tools.
- `list_eval_runs` — List recent eval runs with their aggregate scores. Use this to track quality over time and detect drift.
- `list_extracted_skill_templates` — List reusable skill templates automatically extracted from successful harness runs.
- `list_founder_issue_packets` — List founder issue packets from shared context by workspace, producer, status, or strategic angle.
- `list_learnings` — [DEPRECATED: Use search_all_knowledge instead] List stored learnings. PREFER search_all_knowledge for unified knowledge search across learnings, recon findings, and gaps.
- `list_openclaw_channels` — List messaging channels you can send through.
- `list_pending_sync_operations` — List queued outbound sync operations that still need to be pushed to the web account.
- `list_sandbox_policies` — List all configured sandbox policies with session stats (active sessions, total violations triggered).
- `list_self_directed_delivery_runs` — List recent autonomous delivery runs so operators can reopen or compare them.
- `list_shared_context_peers` — List peers by product, workspace, role, surface, capability, or scope.
- `list_skills` — List all registered skills with their freshness status, source files,
- `list_stale_packets` — List memory blocks and packets that need refresh.
- `list_verification_cycles` — List all verification cycles, optionally filtered by status. Use this to find a cycle ID or review past verifications.
- `list_webmcp_tools` — List all tools discovered from connected WebMCP origins. Shows tool names, descriptions, and input schemas. Optionally filter by origin.
- `list_workspace` — List files in the agent workspace. Shows folder tree with file sizes and dates.
- `listAgentMemory` — List all stored memory keys with their metadata
- `listDocuments` — List all user documents sorted by last modified (most recent first, up to 200).
- `listEntityContexts` — List all tracked entity contexts with pagination. Useful for browsing the knowledge base.
- `listFiles` — List user files, optionally filtered by type (image, video, document, csv, pdf).
- `listFolders` — List all user folders.
- `listSpreadsheets` — List user spreadsheets sorted by last updated.
- `load_diligence_pack` — Load the vertical diligence pack for the current direction.
- `load_session_notes` — Load session notes from the filesystem. Use after context compaction, /clear, or session resume to recover state. Returns notes sorted by recency. Supports filtering by date, category, or keyword.
- `log_context_budget` — Track context window usage to prevent pollution. LLM agents have finite context and, as Anthropic
- `log_tool_call` — Log an MCP tool call for profiling. Called automatically by the NodeBench gateway to track tool usage patterns, cost, and latency. Returns whether the call was redundant.
- `lookup_entity` — Look up a single entity by URI (entity://<slug>) or by canonical name. Backed by the federated search action filtered to nb_entities. Returns the top match
- `meeting_notes_extract_decisions` — Extract decisions, owners, and follow-ups from raw meeting notes.
- `mine_session_patterns` — Analyze tool_call_log and learnings tables to extract recurring success/failure sequences across sessions. Finds common 2-3 tool sequences (bigrams/trigrams), cross-references with result_status to surface failure-prone patterns, and ret…
- `monitor_repo` — Track a GitHub repository
- `multi_criteria_score` — Deterministic weighted multi-criteria decision analysis (MCDM). Takes options with numeric values per criterion, normalizes using min-max scaling, applies directional weights, and returns ranked results. No LLM involved — purely mathemat…
- `nb_filter_receipts` — Filter action receipts by channel, policy, approval state, or direction.
- `nb_filter_tool_activity` — Filter the MCP ledger by tool name, date, or status.
- `nb_get_feed_items` — Get public research feed items surfaced on Home.
- `nb_get_funding_brief` — Get funding intelligence through the active research surface.
- `nb_get_leaderboard` — Get model evaluation leaderboard data for the internal benchmark surface.
- `nb_get_qa_results` — Get the latest QA pipeline results, scores, issues, and governance violations.
- `nb_get_signals` — Get the latest research signals with trend data and source attribution.
- `nb_list_agents` — List available AI agent templates and active conversations.
- `nb_list_escalated_actions` — List escalated actions that triggered policy review or human approval.
- `nb_list_scenarios` — List available eval scenarios with descriptions and difficulty.
- `nb_open_delegation` — Open the delegation surface to review scoped authority and approval gates.
- `nb_open_receipts` — Jump into the live receipts feed from the home surface.
- `nb_review_pending_approvals` — Review approval-gated receipts waiting for a human decision.
- `nb_review_shared_context` — Inspect shared-context peers, packets, and handoffs.
- `nb_search_from_chat` — Run a grounded search from the chat surface.
- `nb_search_reports` — Search saved reports and public packets.
- `nb_search_research` — Search across research signals, briefings, and intelligence reports.
- `nb_view_screenshots` — Get captured route screenshots for visual QA.
- `news_company` — Get recent news articles for a specific company/ticker symbol from Yahoo Finance.
- `news_world` — Get world/market news headlines. Currently returns a placeholder — requires an external news API for full functionality.
- `nodebench_get_app_state` — Get the current application state — which view is active, its capabilities (data endpoints, actions, tools), authentication status, and whether the agent panel is open. Call this first to orient yourself.
- `nodebench_get_capabilities` — Meta-tool: lists all available WebMCP tools with their descriptions. Call this first to understand what you can do with NodeBench.
- `nodebench_get_digest` — Retrieve the latest morning digest — a curated summary of research signals, trending topics, and actionable insights.
- `nodebench_get_screen_context` — Get the current screen
- `nodebench_list_views` — List all available views with their capabilities — titles, descriptions, actions, data endpoints, and tags. Use this to discover what the app offers before navigating. Returns a manifest of all 27+ views.
- `nodebench_query_elements` — Query all agent-annotated interactive elements on the current page. Returns elements with their data-agent-id, action type, label, and target. Use this to understand what you can interact with on the current view.
- `nodebench_search` — Search NodeBench documents, research dossiers, and knowledge base. Returns relevant results with titles, snippets, and metadata.
- `nodebench_search_views` — Search for views by keyword — matches against titles, descriptions, tags, and tool categories. Use this to find the right view for a task.
- `nodebench_traverse_feed` — Traverse content feeds with Moltbook-style sorting (hot, new, top, rising). Supports pagination via cursor. Available feed types: research, signals, documents, agents, funding, activity.
- `nodebench.activity_timeline` — Read the canonical activity ledger for a NodeBench report, including captures, notebook patches, graph clicks, export events, and search/cache decisions.
- `nodebench.compile_interview_packet` — Compile a public interview-prep context pack for a company or person. Resume-specific fit scoring must happen in the calling app.
- `nodebench.context.pack` — Return a compact context pack for a use case like job_match, interview_prep, sales_research, or product_intel. Apps should do private scoring locally.
- `nodebench.dossiers.get` — Get a sourced public dossier for an entity by entity ID, key, name, or domain.
- `nodebench.entities.resolve` — Resolve a public company, person, role, product, investor, school, or source into a stable NodeBench entity ID with aliases and confidence.
- `nodebench.expand_resource` — Expand a Nodebench resource URI (nodebench://org/{key}) by one ring using the requested lens + depth. Returns cards, evidence refs, and next-hop URIs shaped for recursive exploration.
- `nodebench.expand_subject` — Expand a single person, company, event, topic, repo, or document into canonical entity resolution, related entities, recommended angles, and reusable resource URIs.
- `nodebench.get_entity_dossier` — Get a sourced public entity dossier from NodeBench public research memory by entity_key or name/type.
- `nodebench.get_matching_context` — Alias for nodebench.context.pack optimized for app-local matching and scoring flows.
- `nodebench.refresh_resource` — Refresh a stale Nodebench resource URI and return updated metadata, freshness information, and emitted resource URIs.
- `nodebench.render_output` — Render an existing brief or artifact into a target format such as compact alert, ntfy brief, Notion markdown, executive brief, or email digest. Does not recompute research unless explicitly told to.
- `nodebench.report_export_preview` — Prepare a reviewable NodeBench report export. Returns mapped contacts, companies, interactions, follow-ups, claims, and sources before any completed export.
- `nodebench.research_company` — Run or reuse public-source company research, store verified public claims, and return a compact company dossier.
- `nodebench.research_person` — Run or reuse public-source person research, store verified public claims, and return a compact person dossier.
- `nodebench.search_public_sources` — Search NodeBench public research memory and source cache for public facts about an entity. Private email, resume, and inbox text must not be sent here.
- `open_operating_dashboard` — Start the Operating Dashboard — shows trajectory scores, event ledger, important changes, path replay, time rollups, packet readiness, and recent actions. The ambient intelligence surface for your business. All from local SQLite.
- `overstory_fleet_status` — Read the Overstory multi-agent fleet status — active agents, capabilities, health, worktree state.
- `overstory_mail_log` — Read recent Overstory QA mail messages — capture-complete, stability results,
- `overstory_merge_queue` — Read the Overstory merge queue — pending merges, completed merges,
- `overstory_qa_summary` — Aggregate QA gate results across all routes — per-route stability grades,
- `partnership_target_map` — Map likely partnership targets and why they fit the current wedge.
- `pdf_search_text` — Search text inside a local PDF over selected pages. Returns page numbers and bounded snippets around matches. Deterministic, no network.
- `populate_historicals` — Populate historical financial data from discovered sources. This tool: - Checks NodeBench cache first (instant, free) - Falls back to SEC EDGAR if needed - Extracts revenue, EBITDA, margins, cash flows - Fills in the historical data sect…
- `predict_risks_from_patterns` — Given a task description, predict likely failure modes based on historically similar sessions. Searches the learnings table (FTS) for entries matching the task, finds sessions where similar tools were used and checks their error patterns…
- `pull_profile` — Pull the current company profile and saved context from NodeBench AI into Claude Code. Returns the latest shared-context packets, saved reports, and entity data for a company.
- `pull_report` — Pull a saved report from NodeBench AI into Claude Code. Returns the full report with sections, sources, and next actions.
- `pull_shared_context` — Pull shared-context packets by type, producer, scope, workspace, status, or subject substring.
- `query_daily_brief` — Get today
- `query_funding_entities` — Search funding intelligence from the Convex platform. Filter by company name, round type, or get recent events. Returns structured funding data with investors, amounts, and confidence scores.
- `query_graphify` — Query an existing graphify knowledge graph. Find nodes by label, explore connections,
- `query_research_queue` — View the research task queue from the Convex platform. Shows active and pending research topics with priorities, entities, personas, and quality scores.
- `query_temporal_signals` — Search and retrieve temporal signals with filtering by entity, signal type, status, and date range. Returns formatted signal records from the local temporal store.
- `query_view_data` — Query data from a view
- `quickSearch` — Execute a quick multi-source search query. Returns ranked results from web, news, and academic sources.
- `rank_interventions` — Rank potential interventions by expected trajectory delta. Each intervention includes expected impact, confidence, cost, timeframe, and what evidence would confirm or deny its effect.
- `read_csv_file` — Read a local CSV file and return a bounded table preview (headers + rows). Deterministic, no network.
- `read_docx_text` — Extract text from a local DOCX (Office OpenXML) file. Deterministic, no network.
- `read_emails` — Read emails from an IMAP mailbox over TLS. Requires EMAIL_USER and EMAIL_PASS env vars. Defaults to Gmail IMAP (imap.gmail.com:993). For Gmail, enable IMAP in Settings and use an App Password. Returns emails with headers (from, to, subje…
- `read_image_ocr_text` — Extract text from a local image (PNG/JPG/etc) using OCR (tesseract.js). Deterministic, no network.
- `read_json_file` — Read a local JSON file and return a bounded JSON preview (depth/item/string truncation). Deterministic, no network.
- `read_jsonl_file` — Read a local JSONL file and return bounded parsed rows. Deterministic, no network.
- `read_pdf_text` — Extract text from a local PDF file for selected pages. Returns bounded text with page markers. Deterministic, no network.
- `read_pptx_text` — Extract text from a local PPTX (Office OpenXML) file. Deterministic, no network.
- `read_text_file` — Read a local text file (txt/md/xml/json/etc) and return a bounded text slice. Deterministic, no network.
- `read_workspace_file` — Read a file from the agent workspace. Returns content for text files, metadata for media files.
- `read_xlsx_file` — Read a local XLSX workbook and return a bounded sheet preview (headers + rows). Deterministic, no network.
- `readAgentMemory` — Retrieve previously stored data by key
- `refresh_subconscious` — Get a summary of all subconscious memory blocks and their status.
- `refresh_task_context` — Re-inject the current task context to combat attention drift. After 30+ tool calls, models lose sight of original goals (
- `render_decision_memo` — Render a 1-page executive decision memo from a completed Deep Sim analysis. Combines claim graph, variables, scenarios, interventions, and compounding score into a structured memo with counter-models, forecast check date, and whatWouldCh…
- `research_job_market` — Research job market requirements for a given role or skill set. Provides guidance on in-demand skills, common requirements, and career recommendations. Useful for project ideation, learning priorities, and understanding market needs. Not…
- `resolveAlias` — Resolve an alias (name, ticker, CUSIP, ISIN) to its canonical entity.
- `retention_get_status` — Return the latest retention.sh connection and recent event history from local MCP state.
- `retention_status` — Check retention.sh connection status and QA metrics. Shows team code, QA score, member count, and last sync time. Use to verify retention.sh integration is working.
- `review_paper_as_reviewer` — Simulate a peer reviewer evaluating a paper for a top venue. Default: harsh mode with rejection mindset — only strong contributions change the verdict. Returns structured review: summary, strengths, critical weaknesses, rating (1-10), an…
- `review_pr_checklist` — Structured PR review checklist with verification/eval cross-reference. Validates PR title format, description presence, file change scope, test coverage, and optionally checks NodeBench verification cycle completion. Returns scored check…
- `route_founder_packet` — Route a founder/company request into the canonical company mode, packet type, artifact type, and next action policy.
- `runway_check` — Basic runway check that translates cash and burn into months remaining and flags risk.
- `sandbox_search` — BM25-ranked full-text search across all sandboxed content. Pass multiple queries as an array to batch all questions in one call. Use after sandbox_ingest or sandbox_execute to retrieve relevant snippets without pulling raw data into cont…
- `sandbox_stats` — Show context savings for the current session — per-tool breakdown, total bytes indexed vs returned, savings ratio, and estimated token savings. Use to quantify how much context window space the sandbox has preserved.
- `scan_capabilities` — Analyze a source file for structural code patterns. Returns a capability report showing what the code can structurally DO — state management (hooks, refs, reducers), layout (overlay, sidebar, grid, responsive), interactions (keyboard, dr…
- `scan_dependencies` — Scan a project
- `scan_terminal_security` — Scan project files and dev environment for terminal security threats: Unicode homograph attacks, ANSI escape injections, invisible characters, and suspicious URL patterns. Auto-discovers dotfiles, CI configs, env files, shell scripts, an…
- `scan_webmcp_origin` — One-shot scan: connect to a WebMCP-enabled site, discover tools, cache the manifest, and disconnect. Useful for inventorying WebMCP tools without keeping a browser open. Results are cached to ~/.nodebench/webmcp_cache/.
- `scan_wordpress_updates` — Scan a WordPress site for plugin and theme versions, and optionally check for known vulnerabilities via the WPScan API. Detects plugins/themes from page source and extracts versions from ?ver= query params. If wpscanApiToken is provided,…
- `score_compounding` — Compute the full 8-dimension trajectory score for an entity. Returns trust-adjusted compounding, drift, adaptation velocity, and all sub-scores with explanations. Output includes TrajectoryScoreBreakdown and TrajectorySummaryData.
- `score_scenario_branch` — Score a specific scenario branch against evidence and constraints.
- `scrapling_batch_fetch` — Fetch multiple URLs in parallel with configurable concurrency. Use for competitive analysis, multi-source research, or batch data collection. Up to 20 URLs, 1-10 concurrent fetches. Each URL gets the same tier/proxy config. Returns per-U…
- `scrapling_crawl_status` — Check crawl progress and get collected items. Pass the session_id from scrapling_crawl. Returns status (running/completed/stopped), pages crawled, items with extracted data, and errors. Poll periodically until status is
- `scrapling_extract` — Extract structured data from a URL using CSS or XPath selectors. Zero LLM tokens — deterministic extraction. Use CSS selectors like
- `scrapling_fetch` — Fetch a URL with adaptive scraping. Auto-selects fetcher tier:
- `scrapling_track_element` — Track an element across page versions using Scrapling
- `search` — Search across live web results and stored NodeBench knowledge in one call. Use this instead of deciding between external search and internal memory first.
- `search_all_knowledge` — Search ALL accumulated knowledge in one call: learnings (edge cases, gotchas, patterns), recon findings (across ALL sessions), and resolved gaps from past verifications. Use this before starting any new work to see what the system alread…
- `search_content_archive` — Search past content by theme, title, or keywords using FTS5 full-text search. Use before generating new content to check what
- `search_github` — Search GitHub repositories by query, topic, language, and star count. Useful for discovering libraries, frameworks, prior art, and learning from existing implementations. Returns repo metadata including stars, forks, description, and top…
- `search_learnings` — [DEPRECATED: Use search_all_knowledge instead] Search past learnings. PREFER search_all_knowledge which searches learnings + recon findings + gaps in a unified query.
- `search_memory` — Federated keyword search across NodeBench
- `search_openclaw_gotchas` — Search stored OpenClaw pitfalls, security findings, and best practices.
- `search_report_context` — Search within a single report
- `searchDocuments` — Search documents by title (full-text search).
- `searchEntities` — Search entities by type, sector, or country. Returns up to 50 results.
- `searchEntityContexts` — Search entity contexts by keyword. Returns entity profiles with summaries, tags, sectors, and relationship data.
- `searchResearch` — Search across research content
- `searchThreads` — Full-text search across narrative threads by keyword.
- `seo_audit_url` — Fetch a URL and analyze its SEO elements: title tag, meta description, Open Graph tags (og:title, og:description, og:image), heading hierarchy (h1-h6 counts), images without alt text, canonical URL, robots meta, and structured data (JSON…
- `service_to_dashboard_path` — Map a concept from bespoke service work to a possible dashboard subscription path without losing the local-first wedge.
- `setup_local_env` — Discover and diagnose the local development environment. Checks for available API keys, installed SDKs, Node.js version, package manager, and git status. Returns suggestions for setting up missing components. Use this to help agents boot…
- `share_get_packet_link` — Retrieve a local share link record by share ID.
- `shortest_valid_path` — Return the shortest valid workflow path for the stated objective.
- `solve_bass_clef_age_from_image` — Extract bass-clef note letters from a simple staff image and compute the derived
- `solve_green_polygon_area_from_image` — Compute the area of a green filled polygon in an image by pixel segmentation, calibrating pixel-to-unit scale from nearby purple length labels. Deterministic, no network.
- `solve_red_green_deviation_average_from_image` — Extract red and green numbers from an image, compute population stdev(red) and sample stdev(green), then return their average. Deterministic, no network.
- `solve_storage_upgrade_cost_per_file_from_image` — OCR plan tiers from an image, compute required storage from equally-sized file counts, and return average incremental $/file beyond the current plan limit. Deterministic, no network.
- `submission_readiness_score` — Score whether the company packet is ready for downstream submission or profile export.
- `suggest_optimizations` — Analyze the current session and suggest specific optimizations: cheaper models, cached results, workflow shortcuts, and reusable patterns.
- `suggest_related` — Suggest related items given a root URI (entity://, report://, etc.). PR1 implementation uses the root
- `suggest_tests` — Generate scenario-based test suggestions from a site_map or diff_crawl session. Analyzes crawl findings and generates actionable test cases.
- `summarize_session` — Summarize the current or specified session
- `sync_figma_tokens` — Pull Figma design token variables from a Figma file and compare against the codebase
- `team_alignment_check` — Check whether the team is aligned on the wedge, next move, and moat story.
- `thompson_anti_elitism_lint` — Scan content for elitism, gatekeeping language, and intellectual intimidation. Deterministic banned-phrase detection + readability scoring. Returns CLEAN or FLAGGED with specific fixes.
- `thompson_feynman_edit` — Skeptical Beginner editor — reviews Thompson-written content against 8 rejection criteria. Returns PASS/REWRITE per section with specific fix instructions. Max 3 rewrite cycles.
- `thompson_quality_gate` — Deterministic 10-point quality gate for Thompson Protocol content. Produces a boolean checklist and overall grade (exemplary/passing/needs_work/failing).
- `thompson_visual_map` — Generate precise visual prompts that map 1:1 with content analogies. No generic b-roll — every visual reinforces a specific metaphor from the Thompson-written content.
- `toon_decode` — Convert TOON (Token-Oriented Object Notation) string back to JSON. Use this to parse TOON-encoded data from other agents, tool responses with --toon flag, or any TOON-formatted content. Returns standard JSON that can be used with any tool.
- `toon_encode` — Convert JSON data to TOON (Token-Oriented Object Notation) format. TOON uses ~40% fewer tokens than JSON while maintaining better LLM accuracy (73.9% vs 69.7%). Useful for preparing data for other LLM calls, reducing context window usage…
- `track_entity_changes` — Detect what changed for an entity since a given date.
- `translate_academic` — Translate academic text between Chinese and English, preserving LaTeX commands, citations, equations, and technical terminology. Returns translated text plus a terminology dictionary for consistency checking across sections.
- `traverse_entity_graph` — Find all entities and relationships connected to a starting entity within N hops.
- `traverse_feed` — Traverse content feeds with Moltbook-style sorting.
- `validate_shortcut` — Validate that a proposed shortcut preserves output quality and visibility.
- `verify_concept_support` — Check if a source file contains all required code signatures for a concept. Provide a concept name and a list of regex patterns that MUST exist for the concept to be considered implemented. Returns match score (0-100%), status (Fully/Par…
- `watchlist_get_alerts` — Return watchlist entries with attached change summaries or non-zero alert counts.
- `watchlist_list_entities` — List watched entities from the local founder watchlist.
- `web_search` — Search the web through NodeBench
- `workflow_adoption_scan` — Evaluate how naturally a direction fits current high-frequency user workflows, install surfaces, and maintenance burden.
- `xlsx_aggregate` — Aggregate values from a local XLSX (count/sum/avg/min/max) with optional filters. Deterministic, no network.
- `xlsx_select_rows` — Select rows from a local XLSX using deterministic filters. Returns bounded results (selected columns + matching rows). No network.
- `zip_list_files` — List entries in a local ZIP file. Deterministic, no network.
- `zip_read_text_file` — Read a text file inside a local ZIP archive and return bounded text. Deterministic, no network.
- `accept_shared_task` — Accept a proposed shared-context task.
- `ack_shared_context` — Acknowledge that a peer received and accepted a context packet.
- `add_forecast_evidence` — Add evidence to a forecast
- `add_rss_source` — Register an RSS or Atom feed URL for monitoring. Stored in SQLite for persistent tracking. Validates the feed on add. Use fetch_rss_feeds to pull articles and build_research_digest to generate a digest of new articles.
- `addDocumentToFolder` — Add a document to a folder.
- `archive_content` — Save generated content to the archive for deduplication and theme tracking. Prevents the engine from regenerating similar content. Supports digest, post, report, and brief content types.
- `assign_agent_role` — Assign a specialized role to the current agent session. Roles define focus area and behavioral instructions. Predefined roles: implementer, dedup_reviewer, performance_optimizer, documentation_maintainer, code_quality_critic, test_writer…
- `attach_execution_evidence` — Attach evidence to a live execution trace. Use for URLs, uploaded files, screenshots, render outputs, and truth-boundary notes that support or qualify the workflow output.
- `bind_local_account` — Record explicit local pairing permission so this device can map durable local context to a specific web user and workspace.
- `bootstrap_project` — Register or update your project
- `broadcast_agent_update` — Broadcast a status update to all active agents. Unlike send_agent_message (point-to-point), this creates a message with no specific recipient that all agents can see via check_agent_inbox. Useful for announcing blockers, completed milest…
- `build_before_after_memo` — Build a memo showing the before and after path plus the validation rationale.
- `build_causal_chain` — Construct a causal chain from temporal observations. Nodes must be in chronological order. Each node represents a cause-effect step with timestamp, label, description, and optional evidence links.
- `build_company_packet` — Build the canonical company readiness packet.
- `build_slack_onepager` — Build a Slack-friendly one-page founder report.
- `claim_agent_task` — Claim a task lock so other parallel agents know you
- `claimTask` — Claim a pending task for execution. Returns the task if successful, null if already claimed or dependencies not met.
- `compile_environment_spec` — Generate a simulation environment specification from entity intelligence.
- `complete_autonomy_benchmark` — Finalize an autonomy benchmark run. Computes final score, duration, tool usage stats, and comparison against reference (e.g. Anthropic
- `complete_eval_run` — Finalize an eval run and compute aggregate scores. Returns pass rate, average score, failure patterns, and improvement suggestions.
- `complete_execution_run` — Finish a live execution run by updating session status, trace status, and optional usage metrics. Use this after the workflow either completes or fails.
- `complete_shared_task` — Complete a shared-context task and attach the output packet if one was produced.
- `compress_or_expand_text` — Precisely compress or expand academic text by a target word count. Compress mode: remove filler words, convert clauses to phrases, passive to active. Expand mode: add logical connectors, explicit reasoning, implicit conclusions. Preserve…
- `compute_dimension_profile` — Recompute and persist the DeepTrace dimension profile for an entity. Use after new company evidence, relationship updates, or temporal signals land.
- `configure_channel_preferences` — Set your messaging preferences: which channels to use first,
- `configure_sandbox_policy` — Create or update a security policy for OpenClaw agent sessions.
- `convex_audit_transaction_safety` — Audit Convex functions for transaction safety: multiple ctx.runMutation calls in actions (separate transactions — partial failure risk), read-then-write patterns across query/mutation boundaries (TOCTOU races), and complex check-then-act…
- `convex_generate_plan` — Generate a Convex-specific implementation plan for missing code signatures. Takes the gap analysis from convex_verify_concept and produces step-by-step instructions with Convex-aware injection strategies (schema changes, function registr…
- `convex_generate_rules_md` — Generate or update a Convex rules markdown file from the current gotcha database, recent audit results, and project stats. Outputs to a specified path or returns the content. Use this to keep your AI rules file in sync with accumulated C…
- `convex_record_gotcha` — Record a Convex-specific gotcha, edge case, or pattern for future reference. Stored persistently and searchable via full-text search. Categories: validator, schema, function, deployment, auth, performance, general.
- `convex_schema_migration_plan` — Compare two schema snapshots and generate a migration checklist. Shows added/removed tables, index changes, and risk assessment. Use after convex_snapshot_schema to plan deployments safely.
- `create_forecast` — Create a new forecast with a question, resolution date, and criteria. Optionally set initial probability, base rate, and evidence. Returns forecast ID for subsequent updates.
- `create_proof_pack` — Assemble an immutable proof pack for verification. Bundles a checklist (pass/fail items), optional metrics (tokens, duration, cost), and links to dogfood runs and zero-draft artifacts. Computes pass rate automatically.
- `create_task_bank` — Create or add to a fixed task bank for controlled agent evaluation. Each task defines: initial state (repo snapshot, config), success criteria (deterministic checks), forbidden behaviors, category (bugfix/refactor/integration/UI), and di…
- `create_visual_pr` — End-to-end PR creation: exports screenshots, generates a rich markdown PR body with visual evidence (before/after comparisons, timeline, bug fixes, past sessions), checks git state, pushes, and creates a GitHub PR via
- `createDocument` — Create a new rich-text document with a title and optional initial content blocks.
- `createDocumentWithContent` — Create a document with pre-built ProseMirror JSON content string.
- `createFolder` — Create a new folder for organizing documents.
- `createMission` — Create a new mission with title, type, success criteria, output contract, and budget.
- `createPlan` — Create an explicit task plan as a markdown document with steps marked as pending/in_progress/completed
- `createSpreadsheet` — Create a new spreadsheet with a name.
- `decide_re_update` — Decide whether to update existing instructions or create new files. Implements
- `deeptrace_create_evidence_pack` — Bundle multiple evidence chunks into a named evidence pack. Evidence packs are the unit of provenance — they capture what an agent saw at investigation time.
- `deeptrace_create_passport` — Create or update an agent passport — the scoped identity that defines what an agent can read, spend, sign, and execute. Passports enforce trust tiers (sandbox/supervised/autonomous) with explicit tool-level overrides.
- `deeptrace_ingest_evidence` — Ingest a piece of evidence (article, filing, data point) into the evidence store. Returns a content-addressed chunk ID that can be referenced in receipts and evidence packs.
- `deeptrace_log_receipt` — Log a tamper-evident action receipt. Every agent action should produce a receipt recording what was done, what policy allowed it, and what evidence supports the result. The receipt is content-addressed via SHA-256.
- `delegate_founder_issue` — Create a bounded shared task handoff for a founder issue packet so the weak angle becomes assigned work.
- `delta_handoff` — Generate a delegation packet for handing off work to another agent or teammate. Produces a delta.handoff packet with full context bundle, acceptance criteria, and deadline.
- `delta_memo` — Create a decision-ready memo artifact. Produces a delta.memo packet with recommendation, variables, scenarios, and evidence. Shareable with teammates and stakeholders.
- `delta_retain` — Preserve context for future sessions. Produces a delta.retain packet storing important notes, decisions, meeting outcomes, or research findings that should persist across sessions.
- `dismiss_alert` — Dismiss an important change alert so it no longer appears in proactive alerts. Sets the status to
- `dive_changelog` — Record a change made to fix a bug, design issue, or improve a component. Links before/after screenshots to show what changed visually. Optionally references git commits and changed files. When the dive is re-run after fixes, the changelo…
- `dive_design_issue` — Tag a design inconsistency found during the dive. Covers visual problems like color mismatches, spacing deviations, font inconsistencies, alignment issues, contrast failures, responsive breakage, missing hover/focus states, and more. Lin…
- `dive_generate_tests` — Generate Playwright regression test code from dive findings. Creates test cases from: bugs (verify the fix holds), interaction tests (replay the sequence), design issues (visual regression checks), and component assertions (verify compon…
- `dive_link_backend` — Link a UI component to its backend dependencies. Connect components to API endpoints, Convex queries/mutations/actions, database tables, auth guards, WebSocket channels, or external services. This creates the full-stack traceability map …
- `dive_record_test_step` — Record the actual result of a test step after executing it via the MCP Bridge. Compare expected vs actual, attach a screenshot, and mark pass/fail. When all steps are recorded, the test is automatically completed with an overall status.
- `dive_save_screenshot` — Save a screenshot during a dive session. Pass base64 image data (from bridge
- `draft_email_reply` — Structure an email thread for reply drafting. Parses the thread, extracts context (from, subject, date), and builds a reply prompt with your instructions and desired tone. Returns a structured draft ready to review and send via send_emai…
- `duplicateDocument` — Duplicate a document. Clones content, icon, type. Resets visibility and favorite.
- `end_component_flow` — Complete a component
- `end_dogfood_session` — End a dogfood session with summary metrics: time-to-first-useful-output, delegation success, packet export status, and notes.
- `escalate_shared_task` — Escalate a shared-context task when the assignee cannot complete it cleanly.
- `export_artifact_packet` — Formats a Founder Artifact Packet or memo for export to a specific audience and format.
- `flag_important_change` — Flag a detected important change with impact scoring, affected entities, and optional suggested action. Used by agents to surface significant state transitions.
- `founder_local_synthesize` — Takes gathered local context and synthesizes a complete Founder Artifact Packet.
- `generate_academic_caption` — Generate academic figure or table captions following top-venue conventions. Handles Title Case for noun phrases, Sentence case for full sentences. Removes filler (no
- `generate_flicker_report` — Generate visual flicker report from existing analysis data. Produces SSIM timeline chart (1200x400 PNG, PIL-based, no matplotlib) and side-by-side comparison images for flagged flicker events.
- `generate_grid_collage` — Tile N screenshot images into a single grid collage PNG for visual inspection.
- `generate_implementation_plan` — Generate a structured implementation plan for missing code signatures. Takes the gap analysis from verify_concept_support and produces a step-by-step plan with per-signature requirements and injection strategies. Optionally takes the out…
- `generate_parallel_agents_md` — Generate a portable, framework-agnostic AGENTS.md section for parallel agent coordination. Designed to be dropped into ANY project repo so that AI agents (Claude, GPT, etc.) automatically know how to coordinate in parallel. Includes task…
- `generate_plan_delegation_packet` — Convert a FeaturePlan into an agent-ready delegation packet
- `generate_pr_report` — Generate a rich markdown PR body from a UI Dive session. Compiles visual changes (before/after screenshot comparisons), a unified timeline of all change events, bug fixes with severity badges, design improvements, interaction test result…
- `generate_proposal_memo` — Render a FeaturePlan as a human-readable proposal memo.
- `generate_report` — Compile structured findings, eval results, and quality gate data into a formatted markdown report. Useful for summarizing verification cycles, creating audit trails, or generating stakeholder-ready documents.
- `generate_self_instructions` — Generate self-instructions for the agent in various formats: skills_md (SKILL.md), rules_md (RULES.md), guidelines (internal), claude_md (CLAUDE.md). Includes authoritative source citations.
- `generate_team_install_plan` — Generate a practical install and rollout plan for a founder, solo developer, or small team using NodeBench MCP.
- `generate_voice_scaffold` — Generate starter code for a voice bridge. Returns file contents, setup instructions, and dependency lists for the selected stack. Stacks: whisper_edge (Python, Whisper + Edge TTS), deepgram_cartesia (TypeScript, cloud), browser_webspeech…
- `generate_zero_draft` — Auto-draft an artifact (slack message, email, spec doc, PR draft, architecture note, career plan, or content brief) based on detected signals and causal chains. Returns draft for human approval before sending.
- `graphify_import_to_subconscious` — Import a graphify knowledge graph into NodeBench
- `ingest_dive_screenshots` — Scan a directory for PNG/JPG screenshot files and bulk-import them into the dive session
- `ingest_temporal_observation` — Ingest a raw observation into the temporal substrate (timeSeriesObservations). Supports numeric, categorical, event, and text observations from any source type. Returns observation ID for linking to signals and causal chains.
- `ingest_upload` — Ingest uploaded file content into the NodeBench entity intelligence system.
- `install_nodebench_plugin` — Generate or write a starter .mcp.json entry for NodeBench MCP so a local team member can install the preset quickly.
- `judge_session` — Score a dogfood session on 6 dimensions (1-5 each): truth, compression, anticipation, output, delegation, trust. Returns overall score and records failure classes.
- `link_durable_objects` — Create a durable relationship such as screen -> action, workflow -> run, run -> artifact, or outcome -> evidence.
- `log_benchmark_milestone` — Record completion of a benchmark milestone. Tracks which milestones the agent achieved, time taken, tools used, and whether verification passed.
- `log_gap` — Record a gap found during Phase 2 (Gap Analysis). Gaps are categorized by severity: CRITICAL (protocol violations, security), HIGH (API incompatibilities), MEDIUM (outdated versions), LOW (edge cases).
- `log_phase_findings` — Record findings for the current phase of a verification cycle. Advances the cycle to the next phase if the current phase passes. If it fails, returns guidance to loop back.
- `log_recon_finding` — Record a finding from reconnaissance research. Link it to a recon session and categorize it. Use for both external discoveries (SDK changes, blog posts) and internal findings (codebase patterns, existing implementations).
- `log_test_result` — Record a test result for Phase 4 (Testing & Validation). Tests are organized by layer: static, unit, integration, manual, live_e2e. All layers must pass before proceeding.
- `manage_implementation_packets` — Create and manage implementation packets — structured instructions for Claude Code or other coding agents.
- `manage_task_list` — Manage the workspace task list. Add, update, complete, delete, or list tasks.
- `merge_compose_output` — Judge-gated merge of subtask artifacts into a composed output.
- `merge_research_results` — Merge parallel sub-agent research results into a unified dataset. Takes arrays of records from multiple sources (e.g., Hotel Discovery Agent, Price Agent, Crowd Agent), aligns them by a join key, detects conflicts, and persists the merge…
- `nb_open_approval_queue` — Open the approval queue for held actions.
- `nodebench_create_document` — Create a new document in NodeBench. Supports markdown content with optional metadata tags.
- `nodebench.capture` — Persist a messy event capture into the active NodeBench event workspace without live paid search. Uses event corpus / memory-first policy and returns budget-aware status copy.
- `nodebench.claims.submit_public` — Submit a sourced public claim. The verifier rejects private sources, raw email/resume/private artifact text, and uncited claims.
- `nodebench.link_private_signal_to_public_entity` — Link an app-private signal to a public entity by hash only. Raw Gmail, resume, inbox, and private artifact text must not be sent.
- `nodebench.notebook_append` — Append reviewed text into a NodeBench report notebook through the same Convex-backed report notebook persistence used by the web UI.
- `nodebench.report_export_complete` — Complete a previously previewed NodeBench report export after review. Writes the export completion event to the activity ledger.
- `nodebench.submit_public_claim` — Submit a sourced public claim to NodeBench. The verifier rejects private email/resume-derived text and non-public URLs.
- `nodebench.watch_entity` — Create a watch request for an entity. Current MVP returns the entity and recommended refresh cadence.
- `open_core_boundary_advisor` — Advise what should stay open-core versus proprietary.
- `plan_decompose_mission` — Decompose a mission into subtasks with verifiability routing.
- `polish_academic_text` — Deep-polish academic text for top-venue quality (NeurIPS, ICLR, ICML, ACL). Handles English and Chinese papers. Fixes grammar, enhances clarity, enforces formal academic tone, removes contractions and AI-style vocabulary. Preserves LaTeX…
- `promote_to_eval` — Take findings from a completed verification cycle and promote them into eval test cases. This is how the inner loop feeds the outer loop: Phase 4 test results become eval cases, Phase 5 checklists become scoring rubrics, Phase 6 edge cas…
- `propose_shared_task` — Propose a task handoff between peers with input contexts and required output packet shape.
- `publish_founder_issue_packet` — Turn the weakest founder-direction angle into a durable shared-context issue packet with lineage, proof links, and a reusable resource URI.
- `publish_shared_context` — Publish a structured shared-context packet with subject, claims, evidence refs, freshness, permissions, and lineage.
- `publish_to_queue` — Push content to the LinkedIn content queue on the Convex platform. Content goes through the engagement gate and LLM judge before being scheduled for posting.
- `queue_sync_operation` — Queue an explicit outbound sync operation when a custom workflow needs to push metadata, receipts, or approvals into the account history.
- `rate_packet_usefulness` — Rate a packet
- `record_dogfood_telemetry` — Record a full telemetry row for a dogfood run. Captures surface, scenario, user role, prompt, tool usage, token estimates, latency, cost, and quality scores.
- `record_eval_result` — Record the actual result for a specific eval case. Include what happened, the verdict (pass/fail/partial), and optionally telemetry data and judge notes.
- `record_event` — Record a typed event to the causal event ledger. Supports causal linking via causedByEventId and correlation grouping via correlationId.
- `record_execution_decision` — Record a structured decision on a live execution trace without storing raw hidden reasoning. Use for rankings, selections, rejections, or escalation logic grounded in evidence.
- `record_execution_step` — Record a structured execution step receipt on a live execution trace. Use this for meaningful actions like file inspection, research queries, edits, exports, or issue fixes.
- `record_execution_verification` — Record a verification result on a live execution trace. Use for render checks, formula checks, diff checks, artifact integrity checks, and issue-fix confirmations.
- `record_fix_attempt` — Record a fix attempt with replay proof and regression protection description. Links to a failure case.
- `record_learning` — Store an edge case, gotcha, pattern, or regression discovered during verification. Learnings are searchable via full-text search and prevent repeating the same mistakes. Always record learnings at the end of a verification cycle.
- `record_manual_correction` — Track a human correction to agent output. Every correction is evidence of a system gap — the system should have gotten this right.
- `record_openclaw_gotcha` — Record a discovered OpenClaw pitfall or security finding.
- `record_path_step` — Record a navigation/exploration step in the user
- `record_provenance_receipt` — Persist a durable execution receipt for a tool call, approval, verification, or other meaningful action.
- `record_repeated_question` — Track a question the user asked that NodeBench should have already known. This is the core failure signal — repeat cognition means the system isn
- `record_state_diff` — Record a before/after state change on an entity. Tracks what changed, which fields, and why.
- `record_sync_artifact` — Persist a local artifact with verification state so it can be replayed, reviewed, and optionally synced to the web account.
- `record_sync_outcome` — Persist an outcome with user value, stakeholder value, evidence, and status so the system always resolves work to an inspectable result.
- `recordCanaryRun` — Record a new canary benchmark run with throughput and quality scores.
- `register_component` — Register a UI component in the dive tree. Components form a hierarchy: page → section → form/modal/list → button/input/link. Set parentId to nest under an existing component (null for top-level). The main agent registers the initial tree…
- `register_shared_context_peer` — Register a scoped peer with product, role, surface, capabilities, and heartbeat metadata for shared-context coordination.
- `register_skill` — Register a skill (rule/memory .md file) with its source documents, update triggers,
- `reject_shared_task` — Reject a proposed shared-context task with a reason.
- `release_agent_task` — Release a task lock after completing work. Updates status and optionally records a progress note for the next agent session. Part of the parallel agent coordination pattern.
- `remove_ai_signatures` — Detect and remove AI-generated writing signatures from academic text. First runs pattern matching for known AI vocabulary (leverage, delve, tapestry, mechanical connectors), then uses LLM to rewrite flagged sections naturally. Returns cl…
- `report` — Produce a human-readable artifact for either a research topic or a decision. If recommendation inputs are provided, this emits a memo. Otherwise it emits a diligence-style report.
- `resolve_forecast` — Resolve a forecast with an outcome. Auto-computes Brier and log scores for binary forecasts. Ambiguous outcomes are excluded from scoring.
- `resolve_founder_issue` — Invalidate a founder issue packet and optionally publish a resolution packet so the issue lifecycle stays explicit.
- `resolve_gap` — Mark a gap as resolved after implementing the fix. Returns remaining gap counts by severity.
- `resolveRoutingRecommendation` — Accept, reject, or expire a routing recommendation.
- `resolveSniffCheck` — Resolve a pending sniff check with approved, rejected, or needs_revision.
- `restoreDocument` — Restore an archived document and its children.
- `retention_register_connection` — Register a retention.sh team connection in local MCP state so QA findings and token savings can flow into founder packets.
- `retention_sync` — Sync data between NodeBench Delta and retention.sh. Pushes delta packets as team context and pulls QA findings as watchlist signals.
- `retention_sync_findings` — Sync retention.sh QA findings, scores, and token savings into local MCP state.
- `sandbox_ingest` — Index arbitrary text into the context sandbox (FTS5). Raw content stays in SQLite — only a compact reference enters context. Use for large outputs, API responses, file contents, or any data you want searchable without flooding the contex…
- `save_research_resource` — Save a research resource with URL, source citation, tags, and notes.
- `save_session_note` — Persist a critical finding, decision, or progress note to the filesystem. Notes survive context compaction — call this after every major finding or decision so state is never lost. Writes to ~/.nodebench/notes/ as dated markdown files.
- `scaffold_directory` — Scaffold directory structure following OpenClaw patterns. Creates organized subdirectories and placeholder files for: agent_loop, telemetry, evaluation, verification, multi_channel, self_learning, governance.
- `scaffold_nodebench_project` — Create a complete project template pre-configured for nodebench-mcp. Generates: package.json, AGENTS.md, .mcp.json, .parallel-agents/, .github/workflows/, tsconfig.json, .gitignore, README.md, and src/ directory. Everything an agent need…
- `scaffold_openclaw_project` — Generate a starter project for OpenClaw + NodeBench.
- `scaffold_openclaw_sandbox` — Generate Docker/WSL2/Podman setup files for running OpenClaw in an isolated environment.
- `scaffold_research_pipeline` — Generate a complete, standalone Node.js project for an automated research digest pipeline. Creates: package.json, main script (RSS subscribe → fetch → digest → email), cron setup, .env template, and README with setup instructions. The ge…
- `send_agent_message` — Send a message to another agent by session ID or role. Enables asynchronous inter-agent communication for task handoffs, status reports, blockers, and findings. Messages persist in SQLite so agents spawned later can read them.
- `send_email` — Send an email via SMTP over TLS. Requires EMAIL_USER and EMAIL_PASS env vars. Defaults to Gmail SMTP (smtp.gmail.com:465). For Gmail, use an App Password (Google Account → Security → 2-Step Verification → App passwords). Override host/po…
- `send_openclaw_message` — Send a message through any connected channel.
- `send_peer_message` — Send a direct structured message to a peer without routing everything through a central orchestrator.
- `sendMessage` — Send a message to the live chat run
- `set_watchdog_config` — Configure the background watchdog that continuously monitors system health.
- `setup_operator_profile` — Set up your profile to customize how the AI assistant works for you.
- `share_create_packet_link` — Create a durable local share link record for a packet or founder memo so it can be rendered or synced later.
- `sniff_record_human_review` — Record a human sniff-check for a subtask or merge output.
- `start_component_flow` — Claim a component for traversal by a specific subagent. Marks it as
- `summarize` — Turn raw context into a compact brief with key points and optional persistence. This is the fast human-readable artifact when you do not need a full diligence packet.
- `sync_company` — Push a company profile into NodeBench AI from Claude Code. Extracts company truth from a summary you provide (codebase analysis, docs, notes) and publishes it as a shared-context packet that NodeBench AI can consume.
- `sync_daily_brief` — Sync daily brief + narrative data from Convex to local SQLite. Requires CONVEX_SITE_URL and MCP_SECRET environment variables. Returns sync summary with row counts and timing.
- `sync_operator_profile` — Sync the Operator Profile to the local filesystem at ~/.nodebench/USER.md.
- `sync_report` — Push a report artifact from Claude Code into NodeBench AI. The report is saved locally and published as a shared-context packet for the web app to consume.
- `sync_skill` — Resync a stale skill after applying updates. Recomputes source hashes, updates
- `synthesize_extension_plan` — Synthesize a plan for extending or deepening an existing feature.
- `synthesize_feature_plan` — Synthesize a phased feature implementation plan conditioned on founder context,
- `synthesize_integration_proposal` — Synthesize an integration plan for an external tool, API, or framework.
- `synthesize_recon_to_learnings` — Convert recon findings into persistent learnings. Recon findings are ephemeral research notes; learnings are the distilled, searchable knowledge base. This tool reviews recent recon findings and creates learnings from the most actionable…
- `tag_ui_bug` — Tag a bug to a specific component (and optionally a specific interaction). Bugs are categorized by severity (critical/high/medium/low) and category (visual, functional, accessibility, performance, responsive, ux, content, security). Each…
- `thompson_write` — Transform complex content into Thompson Protocol format — plain English mandate, intuition-before-mechanics, analogy-per-concept. Returns structured sections with jargon translations and readability scores.
- `track` — Add, check, remove, or list tracked entities with one workflow tool. The default path optimizes for watched entities that can feed future nudges and brief artifacts.
- `track_action` — Record any significant action with before/after state, reasoning, and temporal metadata. Auto-captures session, day, week, month, quarter, year.
- `track_intent` — Track a user intent that should survive context window compaction. On
- `track_milestone` — Record a significant milestone (phase complete, deploy, ship, launch, pivot, decision) with optional evidence and metrics.
- `update_agents_md` — Read, append, or update sections in the AGENTS.md file. This file contains instructions for AI agents working on the project. Use
- `update_company_truth` — Update a subconscious memory block with new information.
- `update_forecast_probability` — Update a forecast
- `updateDocument` — Update document fields: title, content, icon, visibility, favorite status.
- `updatePlanStep` — Update the status or notes of a specific step in a task plan
- `upsert_durable_object` — Register or update a durable local object so views, tools, workflows, runs, artifacts, and outcomes share one replayable identity spine.
- `upsertEntity` — Create or update a canonical entity record (company, person, fund, etc.).
- `watchlist_add_entity` — Add an entity to the local founder watchlist with alert preferences and optional strategic-angle linkage.
- `watchlist_refresh_entities` — Refresh watchlist timestamps and optionally attach change summaries for watched entities.
- `write_workspace_file` — Create or update a file in the agent workspace (~/.nodebench/workspace/).
- `writeAgentMemory` — Store intermediate results or data for later retrieval. Use this to avoid context window overflow.
- `zip_extract_file` — Extract a single file from a local ZIP archive to a local output directory (zip-slip safe). Deterministic, no network.

## Related servers

- UnClick (1658 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Yaver (811 tools) — https://policylayer.com/tools/io-github-kivanccakmak-yaver.md
- Binance MCP Server (734 tools) — https://policylayer.com/tools/nirholas-binance-mcp.md
- Fortimanager (584 tools) — https://policylayer.com/tools/jmpijll-fortimanager-mcp.md
- Crow (578 tools) — https://policylayer.com/tools/kh0pper-crow.md
- TinyFn (572 tools) — https://policylayer.com/tools/io-tinyfn-tinyfn.md
- Mcp (571 tools) — https://policylayer.com/tools/io-github-2s-io-mcp.md
- GoHighLevel MCP Server (566 tools) — https://policylayer.com/tools/busybee3333-go-high-level-mcp-2026-complete.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-homenshum-nodebench · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/io-github-homenshum-nodebench