# Hamza Agent Hub 252 MCP server

Agent View of the PolicyLayer registry record for Hamza Agent Hub 252: identity, probed posture, risk grade, and all 582 tools classified. HTML page: https://policylayer.com/tools/hamza-agent-hub-252

## Facts

- Server id: `hamzachallenge3-dev/hamza-agent-hub-252`
- Homepage: https://github.com/hamzachallenge3-dev/hamza-agent-hub-252
- Registry record: grade F, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 582
- Tool categories present: Destructive, Execute, Financial, Read, Write
- Tags: hamza agent hub 252, payments, admin, automation
- Record last modified: 2026-10-20T05:06:50.568Z

## Tools (581)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `agent_terminate` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/agent-terminate.md |
| `agentdb_batch` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-batch.md |
| `agentdb_causal-edge-delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-causal-edge-delete.md |
| `agentdb_causal-node-delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-causal-node-delete.md |
| `agentdb_hierarchical-delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-hierarchical-delete.md |
| `agenticow_rollback` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-rollback.md |
| `autopilot_reset` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-reset.md |
| `cancel_task` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/cancel-task.md |
| `config_reset` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/config-reset.md |
| `federation_wg_keyrotate` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/federation-wg-keyrotate.md |
| `hooks_intelligence-reset` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-reset.md |
| `hooks_worker-cancel` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/hooks-worker-cancel.md |
| `iot_device_remove` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/iot-device-remove.md |
| `iot_device_unpair` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/iot-device-unpair.md |
| `iot_firmware_rollout_rollback` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/iot-firmware-rollout-rollback.md |
| `iot_fleet_delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/iot-fleet-delete.md |
| `iot_fleet_remove_device` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/iot-fleet-remove-device.md |
| `managed_agent_terminate` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/managed-agent-terminate.md |
| `memory_delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/memory-delete.md |
| `policy_revoke` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/policy-revoke.md |
| `ruvector_delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-delete.md |
| `session_delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/session-delete.md |
| `system_reset` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/system-reset.md |
| `task_cancel` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/task-cancel.md |
| `teammate_cleanup` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/teammate-cleanup.md |
| `wasm_agent_reset` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-reset.md |
| `wasm_gallery_remove_custom` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-remove-custom.md |
| `workflow_cancel` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/workflow-cancel.md |
| `workflow_delete` | Destructive | Critical | https://policylayer.com/tools/hamza-agent-hub-252/workflow-delete.md |
| `agent_execute` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/agent-execute.md |
| `agent_pool` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/agent-pool.md |
| `agent_spawn` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/agent-spawn.md |
| `agentdb_route` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-route.md |
| `agentdb_semantic-route` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-semantic-route.md |
| `agentdb_session-start` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-session-start.md |
| `autopilot_disable` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-disable.md |
| `autopilot_enable` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-enable.md |
| `autopilot_learn` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-learn.md |
| `autopilot_predict` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-predict.md |
| `benchmark_run` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/benchmark-run.md |
| `browser_back` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-back.md |
| `browser_check` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-check.md |
| `browser_click` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-click.md |
| `browser_close` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-close.md |
| `browser_eval` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-eval.md |
| `browser_fill` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-fill.md |
| `browser_forward` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-forward.md |
| `browser_hover` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-hover.md |
| `browser_navigate` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-navigate.md |
| `browser_open` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-open.md |
| `browser_press` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-press.md |
| `browser_reload` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-reload.md |
| `browser_scroll` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-scroll.md |
| `browser_select` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-select.md |
| `browser_session_end` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-session-end.md |
| `browser_session_record` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-session-record.md |
| `browser_template_apply` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-template-apply.md |
| `browser_type` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-type.md |
| `browser_uncheck` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-uncheck.md |
| `browser_wait` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/browser-wait.md |
| `claims_accept-handoff` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/claims-accept-handoff.md |
| `claims_handoff` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/claims-handoff.md |
| `claims_rebalance` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/claims-rebalance.md |
| `claims_steal` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/claims-steal.md |
| `collective-decide` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/collective-decide.md |
| `coordination_consensus` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/coordination-consensus.md |
| `coordination_load_balance` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/coordination-load-balance.md |
| `coordination_node` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/coordination-node.md |
| `coordination_orchestrate` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/coordination-orchestrate.md |
| `coordination_sync` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/coordination-sync.md |
| `daa_agent_adapt` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/daa-agent-adapt.md |
| `daa_agent_create` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/daa-agent-create.md |
| `daa_cognitive_pattern` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/daa-cognitive-pattern.md |
| `daa_workflow_execute` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/daa-workflow-execute.md |
| `embeddings_init` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-init.md |
| `embeddings_rabitq_build` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-rabitq-build.md |
| `emit-event` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/emit-event.md |
| `execute-workflow` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/execute-workflow.md |
| `federation_bbs_serve` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/federation-bbs-serve.md |
| `federation_consensus` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/federation-consensus.md |
| `federation_init` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/federation-init.md |
| `federation_send` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/federation-send.md |
| `github_workflow` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/github-workflow.md |
| `gt_formula_cook` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/gt-formula-cook.md |
| `gt_formula_execute` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/gt-formula-execute.md |
| `gt_wasm_cook_batch` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/gt-wasm-cook-batch.md |
| `gt_wasm_optimize_convoy` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/gt-wasm-optimize-convoy.md |
| `gt_wasm_parse_formula` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/gt-wasm-parse-formula.md |
| `gt_wasm_resolve_deps` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/gt-wasm-resolve-deps.md |
| `hive-mind_broadcast` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-broadcast.md |
| `hive-mind_consensus` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-consensus.md |
| `hive-mind_init` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-init.md |
| `hive-mind_join` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-join.md |
| `hive-mind_spawn` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-spawn.md |
| `hooks_build-agents` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-build-agents.md |
| `hooks_codemod` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-codemod.md |
| `hooks_coverage-route` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-coverage-route.md |
| `hooks_intelligence_attention` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-attention.md |
| `hooks_intelligence_learn` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-learn.md |
| `hooks_intelligence_trajectory-end` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-trajectory-end.md |
| `hooks_intelligence_trajectory-start` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-trajectory-start.md |
| `hooks_model-route` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-model-route.md |
| `hooks_notify` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-notify.md |
| `hooks_pre-command` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-pre-command.md |
| `hooks_pre-task` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-pre-task.md |
| `hooks_pretrain` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-pretrain.md |
| `hooks_session-start` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-session-start.md |
| `hooks_teammate-idle` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-teammate-idle.md |
| `hooks_worker-dispatch` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hooks-worker-dispatch.md |
| `http_fetch` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/http-fetch.md |
| `hyperbolic_embed_hierarchy` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hyperbolic-embed-hierarchy.md |
| `hyperbolic_entailment_graph` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/hyperbolic-entailment-graph.md |
| `iot_firmware_rollout_advance` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/iot-firmware-rollout-advance.md |
| `managed_agent_create` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/managed-agent-create.md |
| `managed_agent_prompt` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/managed-agent-prompt.md |
| `metaharness_evolve` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-evolve.md |
| `metaharness_redblue` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-redblue.md |
| `metaharness_security_bench` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-security-bench.md |
| `mission_request_action` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/mission-request-action.md |
| `neural_optimize` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/neural-optimize.md |
| `neural_predict` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/neural-predict.md |
| `neural_train` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/neural-train.md |
| `performance_benchmark` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/performance-benchmark.md |
| `performance_optimize` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/performance-optimize.md |
| `performance_profile` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/performance-profile.md |
| `policy_approve` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/policy-approve.md |
| `policy_evaluate` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/policy-evaluate.md |
| `pr_causal_infer` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/pr-causal-infer.md |
| `pr_quantum_topology` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/pr-quantum-topology.md |
| `quantum_annealing_solve` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/quantum-annealing-solve.md |
| `quantum_dependency_resolve` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/quantum-dependency-resolve.md |
| `quantum_grover_search` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/quantum-grover-search.md |
| `quantum_qaoa_optimize` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/quantum-qaoa-optimize.md |
| `quantum_schedule_optimize` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/quantum-schedule-optimize.md |
| `run_agent` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/run-agent.md |
| `run_agent_prompt` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/run-agent-prompt.md |
| `run_command` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/run-command.md |
| `ruvector-attention` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-attention.md |
| `ruvector-gnn` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-gnn.md |
| `ruvector-hyperbolic` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-hyperbolic.md |
| `ruvector-optimize` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-optimize.md |
| `ruvllm_microlora_adapt` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-microlora-adapt.md |
| `ruvllm_sona_adapt` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-sona-adapt.md |
| `rvf_build` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/rvf-build.md |
| `seraphina_guidance` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/seraphina-guidance.md |
| `swarm_init` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/swarm-init.md |
| `task_orchestrate` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/task-orchestrate.md |
| `teammate_approve_plan` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-approve-plan.md |
| `teammate_batch_route` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-batch-route.md |
| `teammate_enable_optimizers` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-enable-optimizers.md |
| `teammate_launch_swarm` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-launch-swarm.md |
| `teammate_push_remote` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-push-remote.md |
| `teammate_route_task` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-route-task.md |
| `teammate_spawn` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-spawn.md |
| `teammate_teleport` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/teammate-teleport.md |
| `terminal_create` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/terminal-create.md |
| `terminal_execute` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/terminal-execute.md |
| `testgen_tdd_repair` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/testgen-tdd-repair.md |
| `wasm_agent_create` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-create.md |
| `wasm_agent_prompt` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-prompt.md |
| `wasm_agent_tool` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-tool.md |
| `wasm_gallery_create` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-create.md |
| `workflow_execute` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/workflow-execute.md |
| `workflow_pause` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/workflow-pause.md |
| `workflow_resume` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/workflow-resume.md |
| `workflow_run` | Execute | High | https://policylayer.com/tools/hamza-agent-hub-252/workflow-run.md |
| `federation_report_spend` | Financial | Critical | https://policylayer.com/tools/hamza-agent-hub-252/federation-report-spend.md |
| `hooks_transfer` | Financial | Critical | https://policylayer.com/tools/hamza-agent-hub-252/hooks-transfer.md |
| `metaharness_gepa` | Other | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-gepa.md |
| `my-tool` | Other | Low | https://policylayer.com/tools/hamza-agent-hub-252/my-tool.md |
| `noop` | Other | Low | https://policylayer.com/tools/hamza-agent-hub-252/noop.md |
| `agent_health` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agent-health.md |
| `agent_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agent-list.md |
| `agent_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agent-metrics.md |
| `agent_mining_queries` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agent-mining-queries.md |
| `agent_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agent-status.md |
| `agentdb_consolidate` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-consolidate.md |
| `agentdb_context-synthesize` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-context-synthesize.md |
| `agentdb_controllers` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-controllers.md |
| `agentdb_graph-pathfinder` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-graph-pathfinder.md |
| `agentdb_graph-query` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-graph-query.md |
| `agentdb_health` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-health.md |
| `agentdb_hierarchical-recall` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-hierarchical-recall.md |
| `agentdb_pattern-search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-pattern-search.md |
| `agenticow_diff` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-diff.md |
| `agenticow_lineage` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-lineage.md |
| `agenticow_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-status.md |
| `aidefence_analyze` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/aidefence-analyze.md |
| `aidefence_has_pii` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/aidefence-has-pii.md |
| `aidefence_is_safe` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/aidefence-is-safe.md |
| `aidefence_scan` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/aidefence-scan.md |
| `aidefence_stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/aidefence-stats.md |
| `analyze_diff` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/analyze-diff.md |
| `analyze_diff-classify` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/analyze-diff-classify.md |
| `analyze_diff-reviewers` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/analyze-diff-reviewers.md |
| `analyze_diff-risk` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/analyze-diff-risk.md |
| `analyze_diff-stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/analyze-diff-stats.md |
| `analyze_file-risk` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/analyze-file-risk.md |
| `autopilot_history` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-history.md |
| `autopilot_log` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-log.md |
| `autopilot_progress` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-progress.md |
| `autopilot_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-status.md |
| `browser_cookie_use` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-cookie-use.md |
| `browser_extract` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-extract.md |
| `browser_get-text` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-get-text.md |
| `browser_get-title` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-get-title.md |
| `browser_get-url` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-get-url.md |
| `browser_get-value` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-get-value.md |
| `browser_screenshot` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-screenshot.md |
| `browser_session_replay` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-session-replay.md |
| `browser_session-list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-session-list.md |
| `browser_snapshot` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/browser-snapshot.md |
| `business_pod_route_backend` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/business-pod-route-backend.md |
| `business_pod_validate` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/business-pod-validate.md |
| `channel_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/channel-list.md |
| `channel_sync` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/channel-sync.md |
| `cite` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/cite.md |
| `claims_board` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/claims-board.md |
| `claims_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/claims-list.md |
| `claims_load` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/claims-load.md |
| `claims_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/claims-status.md |
| `claims_stealable` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/claims-stealable.md |
| `clean_leads` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/clean-leads.md |
| `config_export` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/config-export.md |
| `config_get` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/config-get.md |
| `config_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/config-list.md |
| `context_compact` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/context-compact.md |
| `coordination_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/coordination-metrics.md |
| `cve_lookup` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/cve-lookup.md |
| `daa_learning_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/daa-learning-status.md |
| `daa_performance_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/daa-performance-metrics.md |
| `demo_tool` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/demo-tool.md |
| `embeddings_compare` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-compare.md |
| `embeddings_generate` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-generate.md |
| `embeddings_hyperbolic` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-hyperbolic.md |
| `embeddings_neural` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-neural.md |
| `embeddings_rabitq_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-rabitq-search.md |
| `embeddings_rabitq_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-rabitq-status.md |
| `embeddings_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-search.md |
| `embeddings_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/embeddings-status.md |
| `extract_contacts` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/extract-contacts.md |
| `features_detect` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/features-detect.md |
| `federation_audit` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-audit.md |
| `federation_bbs_identity` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-bbs-identity.md |
| `federation_bbs_peers` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-bbs-peers.md |
| `federation_bbs_sync` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-bbs-sync.md |
| `federation_bbs_watch` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-bbs-watch.md |
| `federation_breaker_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-breaker-status.md |
| `federation_evict` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-evict.md |
| `federation_identity` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-identity.md |
| `federation_join` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-join.md |
| `federation_onboarding` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-onboarding.md |
| `federation_peers` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-peers.md |
| `federation_query` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-query.md |
| `federation_reactivate` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-reactivate.md |
| `federation_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-status.md |
| `federation_sync` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-sync.md |
| `federation_trust` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-trust.md |
| `federation_wg_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/federation-wg-status.md |
| `forge_detect` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/forge-detect.md |
| `get_agent` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/get-agent.md |
| `get-metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/get-metrics.md |
| `git-status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/git-status.md |
| `github_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/github-metrics.md |
| `github_repo_analyze` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/github-repo-analyze.md |
| `github_url_tricks` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/github-url-tricks.md |
| `grounded_query` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/grounded-query.md |
| `gt_agents` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/gt-agents.md |
| `gt_beads_ready` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/gt-beads-ready.md |
| `gt_beads_show` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/gt-beads-show.md |
| `gt_convoy_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/gt-convoy-status.md |
| `gt_formula_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/gt-formula-list.md |
| `gt_wasm_match_pattern` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/gt-wasm-match-pattern.md |
| `guidance` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/guidance.md |
| `guidance_brain` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/guidance-brain.md |
| `guidance_capabilities` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/guidance-capabilities.md |
| `guidance_discover` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/guidance-discover.md |
| `guidance_quickref` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/guidance-quickref.md |
| `guidance_recommend` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/guidance-recommend.md |
| `guidance_workflow` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/guidance-workflow.md |
| `hive-mind_memory` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-memory.md |
| `hive-mind_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-status.md |
| `hooks_coverage-gaps` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-coverage-gaps.md |
| `hooks_coverage-suggest` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-coverage-suggest.md |
| `hooks_explain` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-explain.md |
| `hooks_intelligence` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence.md |
| `hooks_intelligence_pattern-search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-pattern-search.md |
| `hooks_intelligence_stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-stats.md |
| `hooks_intelligence_unified-stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-unified-stats.md |
| `hooks_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-list.md |
| `hooks_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-metrics.md |
| `hooks_model-stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-model-stats.md |
| `hooks_model-verify` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-model-verify.md |
| `hooks_pre-edit` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-pre-edit.md |
| `hooks_route` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-route.md |
| `hooks_session-end` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-session-end.md |
| `hooks_worker-detect` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-worker-detect.md |
| `hooks_worker-list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-worker-list.md |
| `hooks_worker-status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hooks-worker-status.md |
| `html_extract_links` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/html-extract-links.md |
| `hub_agent_audit` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-agent-audit.md |
| `hub_agent_browse` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-agent-browse.md |
| `hub_edge_health` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-edge-health.md |
| `hub_freellmapi_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-freellmapi-status.md |
| `hub_full_roster` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-full-roster.md |
| `hub_health` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-health.md |
| `hub_integrations` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-integrations.md |
| `hub_list_agents` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-list-agents.md |
| `hub_list_packs` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-list-packs.md |
| `hub_tools13_lookup` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hub-tools13-lookup.md |
| `hyperbolic_hierarchy_compare` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hyperbolic-hierarchy-compare.md |
| `hyperbolic_semantic_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hyperbolic-semantic-search.md |
| `hyperbolic_taxonomic_reason` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/hyperbolic-taxonomic-reason.md |
| `iot_custody_epoch` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-custody-epoch.md |
| `iot_device_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-device-list.md |
| `iot_device_pair` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-device-pair.md |
| `iot_device_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-device-status.md |
| `iot_firmware_rollout_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-firmware-rollout-list.md |
| `iot_firmware_rollout_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-firmware-rollout-status.md |
| `iot_fleet_get` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-fleet-get.md |
| `iot_fleet_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-fleet-list.md |
| `iot_fleet_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-fleet-status.md |
| `iot_mesh_topology` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-mesh-topology.md |
| `iot_store_query` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-store-query.md |
| `iot_store_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-store-status.md |
| `iot_telemetry_anomalies` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-telemetry-anomalies.md |
| `iot_telemetry_baseline` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-telemetry-baseline.md |
| `iot_witness_chain` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-witness-chain.md |
| `iot_witness_verify` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/iot-witness-verify.md |
| `list_categories` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/list-categories.md |
| `list_files` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/list-files.md |
| `managed_agent_events` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/managed-agent-events.md |
| `managed_agent_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/managed-agent-list.md |
| `managed_agent_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/managed-agent-status.md |
| `mcp_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/mcp-status.md |
| `memory_bridge_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/memory-bridge-status.md |
| `memory_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/memory-list.md |
| `memory_retrieve` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/memory-retrieve.md |
| `memory_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/memory-search.md |
| `memory_search_unified` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/memory-search-unified.md |
| `memory_stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/memory-stats.md |
| `metaharness_audit_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-audit-list.md |
| `metaharness_audit_trend` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-audit-trend.md |
| `metaharness_drift_from_history` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-drift-from-history.md |
| `metaharness_flywheel` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-flywheel.md |
| `metaharness_genome` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-genome.md |
| `metaharness_mcp_scan` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-mcp-scan.md |
| `metaharness_score` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-score.md |
| `metaharness_similarity` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-similarity.md |
| `metaharness_threat_model` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-threat-model.md |
| `mission_events` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/mission-events.md |
| `mission_get` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/mission-get.md |
| `n8n_workflow_validate` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/n8n-workflow-validate.md |
| `neural_compress` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/neural-compress.md |
| `neural_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/neural-status.md |
| `pattern_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/pattern-search.md |
| `performance_bottleneck` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/performance-bottleneck.md |
| `performance_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/performance-metrics.md |
| `performance_report` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/performance-report.md |
| `policy_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/policy-status.md |
| `pr_coherence_check` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/pr-coherence-check.md |
| `pr_consensus_verify` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/pr-consensus-verify.md |
| `pr_spectral_analyze` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/pr-spectral-analyze.md |
| `pre-browse` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/pre-browse.md |
| `progress_check` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/progress-check.md |
| `progress_summary` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/progress-summary.md |
| `progress_watch` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/progress-watch.md |
| `read_file` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/read-file.md |
| `retrieve-reasoning` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/retrieve-reasoning.md |
| `ruv_github_file` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruv-github-file.md |
| `ruv_github_repo` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruv-github-repo.md |
| `ruv_github_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruv-github-search.md |
| `ruv_registry_latest` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruv-registry-latest.md |
| `ruvector_health` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-health.md |
| `ruvector_index_stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-index-stats.md |
| `ruvector_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-metrics.md |
| `ruvector_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-search.md |
| `ruvllm_chat_format` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-chat-format.md |
| `ruvllm_hnsw_route` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-hnsw-route.md |
| `ruvllm_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-status.md |
| `rvf_extract` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/rvf-extract.md |
| `rvf_verify` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/rvf-verify.md |
| `scan-code` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/scan-code.md |
| `search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/search.md |
| `search_agents` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/search-agents.md |
| `seo_audit_html` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/seo-audit-html.md |
| `session_info` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/session-info.md |
| `session_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/session-list.md |
| `sheets_to_json` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/sheets-to-json.md |
| `swarm_health` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/swarm-health.md |
| `swarm_monitor` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/swarm-monitor.md |
| `swarm_pheromone_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/swarm-pheromone-status.md |
| `swarm_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/swarm-status.md |
| `system_health` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/system-health.md |
| `system_info` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/system-info.md |
| `system_metrics` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/system-metrics.md |
| `system_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/system-status.md |
| `task_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/task-list.md |
| `task_result` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/task-result.md |
| `task_results` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/task-results.md |
| `task_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/task-status.md |
| `task_summary` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/task-summary.md |
| `team_board` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/team-board.md |
| `team_get` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/team-get.md |
| `team_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/team-list.md |
| `team_templates_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/team-templates-list.md |
| `teammate_delegate` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/teammate-delegate.md |
| `teammate_discover_teams` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/teammate-discover-teams.md |
| `teammate_find_optimal_path` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/teammate-find-optimal-path.md |
| `teammate_get_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/teammate-get-status.md |
| `teammate_get_topology_stats` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/teammate-get-topology-stats.md |
| `terminal_history` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/terminal-history.md |
| `terminal_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/terminal-list.md |
| `todo_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/todo-list.md |
| `transfer_detect-pii` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-detect-pii.md |
| `transfer_ipfs-resolve` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-ipfs-resolve.md |
| `transfer_plugin-featured` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-plugin-featured.md |
| `transfer_plugin-info` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-plugin-info.md |
| `transfer_plugin-official` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-plugin-official.md |
| `transfer_plugin-search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-plugin-search.md |
| `transfer_store-download` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-store-download.md |
| `transfer_store-featured` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-store-featured.md |
| `transfer_store-info` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-store-info.md |
| `transfer_store-search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-store-search.md |
| `transfer_store-trending` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/transfer-store-trending.md |
| `wasm_agent_export` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-export.md |
| `wasm_agent_files` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-files.md |
| `wasm_agent_is_stopped` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-is-stopped.md |
| `wasm_agent_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-list.md |
| `wasm_agent_state` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-state.md |
| `wasm_agent_todos` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-todos.md |
| `wasm_agent_tools` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-tools.md |
| `wasm_agent_turn_count` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-turn-count.md |
| `wasm_gallery_active` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-active.md |
| `wasm_gallery_categories` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-categories.md |
| `wasm_gallery_config` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-config.md |
| `wasm_gallery_export` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-export.md |
| `wasm_gallery_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-list.md |
| `wasm_gallery_list_by_category` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-list-by-category.md |
| `wasm_gallery_load_rvf` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-load-rvf.md |
| `wasm_gallery_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-search.md |
| `web_research` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/web-research.md |
| `web_search` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/web-search.md |
| `witness_export` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/witness-export.md |
| `witness_verify` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/witness-verify.md |
| `workflow_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/workflow-list.md |
| `workflow_status` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/workflow-status.md |
| `x_federation_channel_list` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-channel-list.md |
| `x_federation_channel_read` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-channel-read.md |
| `x_federation_claims` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-claims.md |
| `x_federation_join` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-join.md |
| `x_federation_registry` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-registry.md |
| `x_federation_roster` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-roster.md |
| `x_federation_sync` | Read | Low | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-sync.md |
| `agent_update` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agent-update.md |
| `agentdb_causal-edge` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-causal-edge.md |
| `agentdb_feedback` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-feedback.md |
| `agentdb_hierarchical-store` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-hierarchical-store.md |
| `agentdb_pattern-store` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-pattern-store.md |
| `agentdb_session-end` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agentdb-session-end.md |
| `agenticow_branch` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-branch.md |
| `agenticow_checkpoint` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-checkpoint.md |
| `agenticow_ingest` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-ingest.md |
| `agenticow_promote` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/agenticow-promote.md |
| `aidefence_learn` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/aidefence-learn.md |
| `autopilot_config` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/autopilot-config.md |
| `browser_act` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/browser-act.md |
| `browser_session` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/browser-session.md |
| `channel_publish` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/channel-publish.md |
| `claims_claim` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/claims-claim.md |
| `claims_issue` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/claims-issue.md |
| `claims_mark-stealable` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/claims-mark-stealable.md |
| `claims_release` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/claims-release.md |
| `config_import` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/config-import.md |
| `config_set` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/config-set.md |
| `coordination_topology` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/coordination-topology.md |
| `create-workflow` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/create-workflow.md |
| `daa_knowledge_share` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/daa-knowledge-share.md |
| `daa_workflow_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/daa-workflow-create.md |
| `evidence_export` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/evidence-export.md |
| `federation_admit` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/federation-admit.md |
| `federation_bbs_human_join` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/federation-bbs-human-join.md |
| `federation_bbs_publish` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/federation-bbs-publish.md |
| `federation_invite_mint` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/federation-invite-mint.md |
| `federation_publish` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/federation-publish.md |
| `federation_wg_attest` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/federation-wg-attest.md |
| `feedback_record` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/feedback-record.md |
| `git-commit` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/git-commit.md |
| `github_issue_track` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/github-issue-track.md |
| `github_pr_manage` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/github-pr-manage.md |
| `gt_beads_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-beads-create.md |
| `gt_beads_dep` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-beads-dep.md |
| `gt_beads_sync` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-beads-sync.md |
| `gt_convoy_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-convoy-create.md |
| `gt_convoy_track` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-convoy-track.md |
| `gt_formula_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-formula-create.md |
| `gt_mail` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-mail.md |
| `gt_sling` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/gt-sling.md |
| `hive-mind_leave` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-leave.md |
| `hive-mind_shutdown` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hive-mind-shutdown.md |
| `hooks_init` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-init.md |
| `hooks_intelligence_pattern-store` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-pattern-store.md |
| `hooks_intelligence_trajectory-step` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-intelligence-trajectory-step.md |
| `hooks_model-outcome` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-model-outcome.md |
| `hooks_post-command` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-post-command.md |
| `hooks_post-edit` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-post-edit.md |
| `hooks_post-task` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-post-task.md |
| `hooks_session-restore` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-session-restore.md |
| `hooks_task-completed` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hooks-task-completed.md |
| `hub_boss_route` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hub-boss-route.md |
| `hub_freellmapi_chat` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hub-freellmapi-chat.md |
| `hub_tools13_capabilities` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/hub-tools13-capabilities.md |
| `iot_device_register` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/iot-device-register.md |
| `iot_firmware_rollout_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/iot-firmware-rollout-create.md |
| `iot_fleet_add_device` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/iot-fleet-add-device.md |
| `iot_fleet_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/iot-fleet-create.md |
| `iot_store_ingest` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/iot-store-ingest.md |
| `memory_import_claude` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/memory-import-claude.md |
| `memory_migrate` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/memory-migrate.md |
| `memory_remember` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/memory-remember.md |
| `memory_store` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/memory-store.md |
| `memory_usage` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/memory-usage.md |
| `metaharness_bench` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-bench.md |
| `metaharness_oia_audit` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/metaharness-oia-audit.md |
| `mission_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/mission-create.md |
| `mission_plan` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/mission-plan.md |
| `neural_patterns` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/neural-patterns.md |
| `pattern_store` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/pattern-store.md |
| `policy_budget_set` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/policy-budget-set.md |
| `policy_rule_upsert` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/policy-rule-upsert.md |
| `post-browse` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/post-browse.md |
| `pr_memory_gate` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/pr-memory-gate.md |
| `progress_sync` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/progress-sync.md |
| `report_vuln` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/report-vuln.md |
| `results_merge` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/results-merge.md |
| `run_complete` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/run-complete.md |
| `run_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/run-create.md |
| `ruvector_create_index` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-create-index.md |
| `ruvector_insert` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-insert.md |
| `ruvector_update` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvector-update.md |
| `ruvllm_generate_config` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-generate-config.md |
| `ruvllm_hnsw_add` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-hnsw-add.md |
| `ruvllm_hnsw_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-hnsw-create.md |
| `ruvllm_microlora_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-microlora-create.md |
| `ruvllm_sona_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/ruvllm-sona-create.md |
| `session_restore` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/session-restore.md |
| `session_save` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/session-save.md |
| `store-reasoning` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/store-reasoning.md |
| `swarm_pheromone_update` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/swarm-pheromone-update.md |
| `swarm_shutdown` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/swarm-shutdown.md |
| `task_assign` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/task-assign.md |
| `task_complete` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/task-complete.md |
| `task_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/task-create.md |
| `task_update` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/task-update.md |
| `team_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/team-create.md |
| `team_update` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/team-update.md |
| `teammate_broadcast` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/teammate-broadcast.md |
| `teammate_save_memory` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/teammate-save-memory.md |
| `teammate_send_message` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/teammate-send-message.md |
| `teammate_share_transcript` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/teammate-share-transcript.md |
| `teammate_spawn_team` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/teammate-spawn-team.md |
| `teammate_submit_plan` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/teammate-submit-plan.md |
| `teammate_update_context` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/teammate-update-context.md |
| `terminal_close` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/terminal-close.md |
| `todo_add` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/todo-add.md |
| `todo_complete` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/todo-complete.md |
| `wasm_agent_terminate` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/wasm-agent-terminate.md |
| `wasm_gallery_add_custom` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-add-custom.md |
| `wasm_gallery_configure` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/wasm-gallery-configure.md |
| `witness_append` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/witness-append.md |
| `witness_log` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/witness-log.md |
| `workflow_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/workflow-create.md |
| `workflow_template` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/workflow-template.md |
| `write_file` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/write-file.md |
| `x_federation_admit` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-admit.md |
| `x_federation_channel_accept` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-channel-accept.md |
| `x_federation_channel_create` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-channel-create.md |
| `x_federation_channel_grant` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-channel-grant.md |
| `x_federation_channel_publish` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-channel-publish.md |
| `x_federation_invite_mint` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-invite-mint.md |
| `x_federation_publish` | Write | Medium | https://policylayer.com/tools/hamza-agent-hub-252/x-federation-publish.md |

## Tool descriptions

- `agent_terminate` — Remove a Ruflo-tracked agent from the registry and free its swarm slot. Use when you need to (a) clean up a spawned agent so its cost-tracking row finalizes, (b) reclaim a swarm-topology slot for another agent, or (c) end a stuck agent w…
- `agentdb_batch` — Batch operations on AgentDB episodes (insert, update, delete). Note: entries are stored in the AgentDB episodes table, not the memory_search namespace. Use memory_store for entries that should be searchable via memory_search. Use when ge…
- `agentdb_causal-edge-delete` — Delete a causal edge between two memory entries. Returns controller=
- `agentdb_causal-node-delete` — Cascade-delete a causal node and all its incident edges from the SQL fallback. Native graph-node entries are unaffected (no delete API in the binding). Use when generic memory_* tools are wrong because you need AgentDB-specific controlle…
- `agentdb_hierarchical-delete` — Delete a hierarchical-memory entry by key. Returns controller=
- `agenticow_rollback` — agenticow — discard all edits since the most recent checkpoint on an .rvf memory file. Reuses a fresh COW child derived from the checkpoint. Use when a Darwin tick or agent experiment regressed and you want to revert memory state without…
- `autopilot_reset` — Reset autopilot iteration counter and restart the timer. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with autopilot_enable + a goal desc…
- `cancel_task` — Cancel a queued/running task
- `config_reset` — Reset configuration to defaults Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json…
- `federation_wg_keyrotate` — ADR-111 Phase 6: rotate the local WG keypair. Returns the new public key + recommended next steps (republish manifest, peers regenerate their wg-quick config, grace-period destruction of old key). DESTRUCTIVE — the old private key is ove…
- `hooks_intelligence-reset` — Reset intelligence learning state Use when native Bash hooks (via Claude Code\
- `hooks_worker-cancel` — Cancel a running worker Use when native Bash hooks (via Claude Code\
- `iot_device_remove` — Remove a registered device
- `iot_device_unpair` — Unpair from a registered device
- `iot_firmware_rollout_rollback` — Force rollback a firmware rollout
- `iot_fleet_delete` — Delete a fleet
- `iot_fleet_remove_device` — Remove a device from a fleet
- `managed_agent_terminate` — Delete a managed cloud-agent session (stops billing for it) — the CLOUD counterpart of wasm_agent_terminate. Use when native nothing applies because a cloud session keeps billing container time + tokens until deleted. For a local WASM ag…
- `memory_delete` — Remove a stored memory entry by exact (namespace, key). Use when a previously stored decision is invalidated or contains stale data. No native equivalent — Write to a file does not affect the .swarm/memory.db SQLite store.
- `policy_revoke` — Revoke an outstanding policy approval immediately. Use when responding to an incident or when a previously approved action is no longer authorized.
- `ruvector_delete` — Delete vectors by ID.
- `session_delete` — Delete a saved session Use when native conversation memory is wrong because you need durable cross-session state — restoring agent definitions, swarm topology, memory store, breaker history. For in-session continuation only, no tool need…
- `system_reset` — Reset system state Use when native Bash is wrong because you need Ruflo runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status) — those are not in /proc, only in the running daemon. For OS-level info (uptime,…
- `task_cancel` — Cancel a task Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpl…
- `teammate_cleanup` — Cleanup team resources and save state
- `wasm_agent_reset` — Reset a WASM agent — clears messages and turn count so it can be reused across tasks. Use when native Task is wrong because the agent lives in a sandboxed WASM runtime that must be explicitly reset rather than simply re-spawned.
- `wasm_gallery_remove_custom` — Remove a custom template from the WASM gallery by ID. Use when native Bash rm is wrong because custom templates exist only inside the WASM runtime registry and cannot be deleted via filesystem operations.
- `workflow_cancel` — Cancel a workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single linear …
- `workflow_delete` — Delete a workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single linear …
- `agent_pool` — Manage a fixed-size warm pool of pre-spawned agents to skip cold-start cost on bursty workloads. Use when native Task is wrong because (a) you have a queue of similar tasks and want to amortize spawn latency, (b) cost-tracking wants stab…
- `agent_spawn` — Spawn a subagent
- `agentdb_route` — Route a task via AgentDB SemanticRouter or LearningSystem recommendAlgorithm Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern sto…
- `agentdb_semantic-route` — Route an input via AgentDB SemanticRouter for intent classification Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall…
- `agentdb_session-start` — Start a session with ReflexionMemory episodic replay Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall, RaBitQ quanti…
- `autopilot_disable` — Disable autopilot. Agents will be allowed to stop even if tasks remain. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with autopilot_enabl…
- `autopilot_enable` — Enable autopilot persistent completion. Agents will be re-engaged when tasks remain incomplete. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. P…
- `autopilot_learn` — Discover success patterns from past task completions. Requires AgentDB for full functionality. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pa…
- `autopilot_predict` — Predict the optimal next action based on current state and learned patterns. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with autopilot_…
- `benchmark_run` — Execute performance benchmarks (V2 compatible). Deprecated: Use system/metrics instead.
- `browser_back` — Navigate back in browser history Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content …
- `browser_check` — Check a checkbox Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude. …
- `browser_click` — Click an element using ref (@e1) or CSS selector Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating…
- `browser_close` — Close the browser session Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches…
- `browser_eval` — Execute JavaScript in page context Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before conten…
- `browser_fill` — Clear and fill an input element Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content r…
- `browser_forward` — Navigate forward in browser history Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before conte…
- `browser_hover` — Hover over an element using ref (@e1) or CSS selector Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII g…
- `browser_navigate` — Navigate a browser session to an allowed URL. Blocks private/internal addresses, rechecks the landed URL after redirects, and stops on human-verification challenges.
- `browser_open` — Navigate browser to a URL Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches…
- `browser_press` — Press a keyboard key Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Clau…
- `browser_reload` — Reload the current page Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches C…
- `browser_scroll` — Scroll the page Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude. F…
- `browser_select` — Select an option from a dropdown Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content …
- `browser_session_end` — End a recorded browser session: trajectory-end with verdict, rvf compact, AIDefence pre-store gate (best-effort), and AgentDB index in the browser-sessions namespace. Use when native WebFetch is wrong because you need real browser automa…
- `browser_session_record` — Open a named, traced browser session: allocate an RVF cognitive container, begin a ruvector trajectory, then open the URL via agent-browser. Returns the session id and rvf path. Use when native WebFetch is wrong because you need real bro…
- `browser_template_apply` — Fetch a recipe from the browser-templates AgentDB namespace and return it for caller-level execution. Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, repl…
- `browser_type` — Type text with key events (for autocomplete, etc.) Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gati…
- `browser_uncheck` — Uncheck a checkbox Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude…
- `browser_wait` — Wait for a condition Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Clau…
- `claims_accept-handoff` — Accept a pending handoff Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For trusted in-sess…
- `claims_handoff` — Request handoff of an issue to another claimant Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged o…
- `claims_rebalance` — Suggest or apply load rebalancing across agents Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged o…
- `claims_steal` — Steal a stealable issue Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For trusted in-sessi…
- `collective-decide` — Request collective decision from agents
- `coordination_consensus` — Manage consensus protocol with BFT, Raft, or Quorum strategies Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-o…
- `coordination_load_balance` — Configure load balancing Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task is fine.
- `coordination_node` — Manage coordination nodes Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task is f…
- `coordination_orchestrate` — Orchestrate multi-agent coordination Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, nativ…
- `coordination_sync` — Synchronize state across nodes Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task…
- `daa_agent_adapt` — Trigger agent adaptation based on feedback Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. Fo…
- `daa_agent_create` — Create a decentralized autonomous agent Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For s…
- `daa_cognitive_pattern` — Analyze or change cognitive patterns Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For stat…
- `daa_workflow_execute` — Execute a DAA workflow Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For static one-shot ag…
- `embeddings_init` — Initialize the ONNX embedding subsystem with hyperbolic support Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the…
- `embeddings_rabitq_build` — Build RaBitQ 1-bit quantized index from stored embeddings (32× compression). Pre-filters candidates via Hamming scan before exact rerank. Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings…
- `emit-event` — Emit an event to subscribers
- `execute-workflow` — Execute a workflow
- `federation_bbs_serve` — agentbbs Phase 2 — start the read-only pull endpoint peers fetch from (GET /agentbbs/v1/rooms/:roomId/envelopes). Binds 127.0.0.1 unless bindHost is given explicitly, so room contents are never exposed on a routable interface by accident…
- `federation_consensus` — Propose a federated consensus operation across all active peers
- `federation_init` — Initialize federation on this node with a manifest and begin discovery
- `federation_send` — Send a message to a federated peer through the PII pipeline and security gates. Optional budget controls (ADR-097): maxHops defaults to 8 to prevent recursive delegation; maxTokens/maxUsd cap cumulative spend across the hop chain.
- `github_workflow` — Manage GitHub Actions workflows Use when native Bash / file tools are wrong because this MCP tool exposes Ruflo-specific state or controllers that have no shell equivalent. For tasks that fit a one-line native command, prefer that.
- `gt_formula_cook` — Cook a formula into a protomolecule with variable substitution (WASM accelerated)
- `gt_formula_execute` — Execute a formula to create beads/molecules in Gas Town
- `gt_wasm_cook_batch` — Batch cook multiple formulas using WASM for maximum performance
- `gt_wasm_optimize_convoy` — Optimize convoy execution order using WASM graph algorithms
- `gt_wasm_parse_formula` — Parse TOML formula content to AST using WASM (352x faster than JavaScript)
- `gt_wasm_resolve_deps` — Resolve bead dependencies using WASM (topological sort, cycle detection, critical path)
- `hive-mind_broadcast` — Broadcast message to all workers Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagent, …
- `hive-mind_consensus` — Propose or vote on consensus with BFT, Raft, or Quorum strategies Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded …
- `hive-mind_init` — Initialize the hive-mind collective Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagen…
- `hive-mind_join` — Join an agent to the hive-mind Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagent, na…
- `hive-mind_spawn` — Spawn workers and automatically join them to the hive-mind (combines agent/spawn + hive-mind/join) Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker ag…
- `hooks_build-agents` — Generate optimized agent configurations from pretrain data Use when native Bash hooks (via Claude Code\
- `hooks_codemod` — Apply a deterministic, $0 (no-LLM) code transform — the real Tier-1 execution path (ADR-143). Supported intents: var-to-const, remove-console, add-logging. Uses the TypeScript compiler with formatting-preserving edits (comments/whitespac…
- `hooks_coverage-route` — Route task to agents based on test coverage gaps (ruvector integration)
- `hooks_intelligence_attention` — Compute attention-weighted similarity using MoE/Flash/Hyperbolic Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_learn` — Force immediate SONA learning cycle with EWC++ consolidation Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_trajectory-end` — End trajectory and trigger SONA learning with EWC++ Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_trajectory-start` — Begin SONA trajectory for reinforcement learning Use when native Bash hooks (via Claude Code\
- `hooks_model-route` — Route task to optimal Claude model (haiku/sonnet/opus) based on complexity Use when native Bash hooks (via Claude Code\
- `hooks_notify` — Send cross-agent notification Use when native Bash hooks (via Claude Code\
- `hooks_pre-command` — Assess risk before executing a command Use when native Bash hooks (via Claude Code\
- `hooks_pre-task` — Record task start and get agent suggestions with intelligent model routing (ADR-026) Use when native Bash hooks (via Claude Code\
- `hooks_pretrain` — Analyze repository to bootstrap intelligence (4-step pipeline) Use when native Bash hooks (via Claude Code\
- `hooks_session-start` — Initialize a new session and auto-start daemon Use when native Bash hooks (via Claude Code\
- `hooks_teammate-idle` — Agent Teams hook — fired when a teammate agent finishes its turn; reports whether a pending task can be auto-assigned. Use when native Task is wrong because you have a persistent multi-agent team with a shared task list and want idle wor…
- `hooks_worker-dispatch` — Dispatch a background worker for analysis/optimization tasks Use when native Bash hooks (via Claude Code\
- `http_fetch` — ADR-164 §5.1.8 — HTTP probe primitive for business-pod ops benches (synthetic 200/500 endpoint checks, third-party status pages). Default-secure: blocks file://, ftp://, RFC-1918 / loopback / link-local hosts unless CLAUDE_FLOW_HTTP_FETC…
- `hyperbolic_embed_hierarchy` — Embed hierarchical structure in Poincare ball. Uses hyperbolic geometry for optimal tree representation with logarithmic distortion.
- `hyperbolic_entailment_graph` — Build and query entailment graphs using hyperbolic embeddings. Supports transitive closure and pruning strategies.
- `iot_firmware_rollout_advance` — Advance a firmware rollout to next stage
- `managed_agent_create` — Spin up an Anthropic-managed cloud agent (Agent + Environment + Session) — the CLOUD counterpart of wasm_agent_create. Use when wasm_agent_create (local WASM sandbox) is wrong because the task is long-running/async (minutes-hours), needs…
- `managed_agent_prompt` — Send a user turn to a managed cloud-agent session and wait for it to go idle, returning the assistant text + a tool-use trace — the CLOUD counterpart of wasm_agent_prompt. Use when wasm_agent_prompt (local WASM) is wrong because the work…
- `metaharness_evolve` — ADR-153 — Darwin Mode: mutate one of seven harness policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, promote only measured wins. The WRITE layer that closes the…
- `metaharness_redblue` — Adversarial red/blue LLM testing via @metaharness/redblue — generates attacks across OWASP LLM Top-10 / NIST AI RMF families (prompt injection, tool misuse, data leakage, jailbreaks, denial-of-wallet), runs them against an LLM target YOU…
- `metaharness_security_bench` — ADR-153 — upstream Darwin Shield (their own ADR-155): evolves a champion security-detection harness against a 10-vuln/9-decoy ground-truth corpus and grades on TPR/FPR/patch-pass/repro/unsafe vs four baselines (B0 static, B1 LLM-single-p…
- `mission_request_action` — Request a scoped mission control action: requestAuthorization, pause or cancel (admit and resume report executor-unavailable until a durable executor is admitted). Use when a person or agent wants a running or planned mission to change c…
- `neural_optimize` — Optimize neural model performance Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-…
- `neural_predict` — Make predictions using a neural model Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. …
- `neural_train` — Train a neural model Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-path for one-…
- `performance_benchmark` — Run performance benchmarks Use when native shell timing (
- `performance_optimize` — Apply performance optimizations Use when native shell timing (
- `performance_profile` — Profile specific component or operation Use when native shell timing (
- `policy_approve` — Issue a scoped, expiring, limited-use human approval. Use when policy_evaluate returns approval_required; self-approval is rejected.
- `policy_evaluate` — Evaluate an agent action against ADR-324 policy and persist a tamper-evident decision receipt. Use when a consequential tool, deployment, network, spend, or promotion action needs authorization.
- `pr_causal_infer` — Perform causal inference using do-calculus
- `pr_quantum_topology` — Compute quantum topology features (Betti numbers, persistence)
- `quantum_annealing_solve` — Solve combinatorial optimization using quantum annealing simulation. Supports QUBO, Ising, SAT, Max-Cut, TSP, and dependency problems.
- `quantum_dependency_resolve` — Resolve complex dependency graphs using quantum-inspired optimization. Handles version conflicts, minimizes package size or vulnerabilities.
- `quantum_grover_search` — Grover-inspired search with quadratic speedup for unstructured search problems. Provides O(sqrt(N)) query complexity.
- `quantum_qaoa_optimize` — Optimize using Quantum Approximate Optimization Algorithm. Best for Max-Cut, portfolio optimization, scheduling, and routing problems.
- `quantum_schedule_optimize` — Optimize task scheduling using quantum algorithms. Minimizes makespan, cost, or maximizes resource utilization with dependency constraints.
- `run_agent` — Queue an agent from any pack. Use hub-boss to differentiate work across Desk + ECC68 + Forge + Tools13.
- `run_agent_prompt` — Use this when the user gives a concrete task for a specific agent. Returns the agent instructions combined with the task, ready to follow (or to copy into any AI chat).
- `run_command` — Run a shell command as HUB_SANDBOX_USER (default agentbox) under the sandbox work dir; HTTP secret-path only
- `ruvector-attention` — Execute attention mechanism (39 types: multi-head, flash, sparse, linear, etc.)
- `ruvector-gnn` — Execute GNN layer (GCN, GAT, GraphSAGE, GIN, MPNN, EdgeConv)
- `ruvector-hyperbolic` — Hyperbolic embedding operations (Poincare ball, Lorentz hyperboloid)
- `ruvector-optimize` — Self-learning query optimization and index tuning
- `ruvllm_microlora_adapt` — Adapt MicroLoRA weights with quality feedback. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent per-call cost. For…
- `ruvllm_sona_adapt` — Run SONA instant adaptation with a quality signal. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent per-call cost.…
- `rvf_build` — Build RVF container
- `seraphina_guidance` — Ask Seraphina for guidance on a goal. The admin token is OPTIONAL: anonymous and OAuth callers use a shared budget, while an operator token lifts the cap and unlocks high-cost tiers.
- `swarm_init` — Initialize a swarm with persistent state tracking Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace, o…
- `task_orchestrate` — Orchestrate a task
- `teammate_approve_plan` — Approve a submitted plan
- `teammate_batch_route` — Route multiple tasks to teammates optimally, avoiding over-assignment.
- `teammate_enable_optimizers` — Enable BMSSP-powered optimization for team topology and task routing.
- `teammate_launch_swarm` — Launch swarm to execute an approved plan
- `teammate_push_remote` — Push team to Claude.ai remote session
- `teammate_route_task` — Route a task to the best-suited teammate using semantic matching
- `teammate_spawn` — Spawn a new teammate in a team. Returns AgentInput for Claude Code Task tool.
- `teammate_teleport` — Teleport team to a new context/working directory
- `terminal_create` — Create a new terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine.
- `terminal_execute` — Execute a command in a terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine.
- `testgen_tdd_repair` — ADR-175-inspired Test-Driven Repair. Use when you have a failing test and want a verified, bounded-cost fix. Spawns a bounded headless
- `wasm_agent_create` — Create a sandboxed WASM agent with virtual filesystem (no OS access). Optionally use a gallery template. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, determini…
- `wasm_agent_prompt` — Send a prompt to a WASM agent and get a response. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, deterministic replay. Pair with wasm_gallery_search to find a pu…
- `wasm_agent_tool` — Execute a tool on a WASM agent sandbox. Tools: read_file, write_file, edit_file, write_todos, list_files. Use flat format: {tool, path, content, ...}. Use when native Task is wrong because the workload needs sandboxed isolation — untrust…
- `wasm_gallery_create` — Create a WASM agent from a gallery template. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, deterministic replay. Pair with wasm_gallery_search to find a publish…
- `workflow_execute` — Execute a workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single linear…
- `workflow_pause` — Pause a running workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single …
- `workflow_resume` — Resume a paused workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single …
- `workflow_run` — Run a workflow from a template or file Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps.…
- `federation_report_spend` — ADR-097 Phase 3 upstream: report the actual cost of a completed federated call. Fans out to the cost-tracker bus (via the integrator-wired SpendReporter) and the breaker service (so its in-memory rolling buffer is fed). Both targets are …
- `hooks_transfer` — Transfer learned patterns from another project Use when native Bash hooks (via Claude Code\
- `metaharness_gepa` — GEPA genome operations from the
- `my-tool` — My custom tool
- `noop` — Does nothing
- `agent_health` — Report measured agent_execute provider-call outcomes over the last 20 calls: API success-ratio health (0-1), error rate, and response-latency p50/p95. This does not measure task correctness. Agents with no observed calls have unknown hea…
- `agent_list` — List every Ruflo-tracked agent in the registry with its type, model, status, and taskCount. Use when native Task tool is wrong because you need to see the swarm-wide agent inventory across turns (which agents exist, their roles, their co…
- `agent_metrics` — Get performance metrics for agents (V2 compatible). Deprecated: Use agent/status with includeMetrics instead.
- `agent_mining_queries` — Curated GitHub queries to mine agents/skills/MCP
- `agent_status` — Get subagent status
- `agentdb_consolidate` — Request memory consolidation. Use when checking whether AgentDB can consolidate retained memories; native file edits cannot perform controller consolidation. Currently returns unsupported when the installed controller is a no-op stub; no…
- `agentdb_context-synthesize` — Synthesize context from stored memories for a given query Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall, RaBitQ q…
- `agentdb_controllers` — List all AgentDB v3 controllers and their initialization status Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall, Ra…
- `agentdb_graph-pathfinder` — Multi-algorithm native graph pathfinder (ADR-130 Phase 5). Use when agentdb_graph-query k-hop is not enough — pathfinder supports personalized-pagerank, dynamic-mincut, spectral-sparsify, temporal-centrality, connected-component-churn, a…
- `agentdb_graph-query` — Unified graph traversal across the knowledge graph (ADR-130). K-hop queries read committed graph_edges relationships through SQL; a separately populated native graph is not evidence of retained-history coverage. Inspect appliedDepth/trun…
- `agentdb_health` — Get AgentDB v3 controller health status including cache stats and attestation count Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, patt…
- `agentdb_hierarchical-recall` — Recall from hierarchical memory with optional tier filter Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall, RaBitQ q…
- `agentdb_pattern-search` — Search patterns via ReasoningBank controller with BM25+semantic hybrid Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/rec…
- `agenticow_diff` — agenticow — show what a branch changed relative to its lineage: {added, overridden, deleted} vector-id lists. Use when you are about to promote and want to preview the exact merge, or when auditing what a branch actually wrote. Diffing b…
- `agenticow_lineage` — agenticow — walk the COW chain of an .rvf memory file: an ordered list of nodes (role working|checkpoint|base, id, label, parent, createdAt, mutations, tombstones). Use when you need branch history — to find checkpoint ids for a targeted…
- `agenticow_status` — agenticow — health/geometry of an .rvf memory file: {totalVectors, totalSegments, fileSize, currentEpoch, deadSpaceRatio, readOnly, chainDepth, dimension, metric}. Use when you need to check vector count before/after ingest, spot compact…
- `aidefence_analyze` — Deep analysis of input for specific threat types with similar pattern search and mitigation recommendations. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any to…
- `aidefence_has_pii` — Check if input contains PII (emails, SSNs, API keys, passwords, etc.). Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted input (brows…
- `aidefence_is_safe` — Quick boolean check if input is safe. Fastest option for simple validation. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted input (…
- `aidefence_scan` — Scan input text for AI manipulation threats (prompt injection, jailbreaks, PII). Returns threat assessment with <10ms latency. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner…
- `aidefence_stats` — Get AIDefence detection and learning statistics. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted input (browser scrape, federation …
- `analyze_diff` — Heuristically analyze git diff paths, changed lines, and one-commit subjects for risk and classification. Use when preparing a review that needs a quick evidence-based summary; inspect the diff for final judgment.
- `analyze_diff-classify` — Heuristically classify a git diff from changed lines, file paths, and a single-commit subject when available. Use when you need a coarse change category; inspect the diff to confirm.
- `analyze_diff-reviewers` — Suggest reviewer roles from git diff paths and risk; does not identify people or read CODEOWNERS. Use when triaging expertise for a change, then consult CODEOWNERS to assign people.
- `analyze_diff-risk` — Heuristically assess git diff risk from changed file paths, sizes, and status. Use when triaging which files merit closer human review; this is not a security guarantee.
- `analyze_diff-stats` — Count changed files, additions, and deletions in a git diff. Use when you need a quick size summary before inspecting the full patch.
- `analyze_file-risk` — Heuristically assess risk for a file path and optional change metadata. Use when triaging a changed file for focused review; inspect the source for final judgment.
- `autopilot_history` — Search past completion episodes by keyword. Requires AgentDB. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with autopilot_enable + a goal…
- `autopilot_log` — Retrieve the autopilot event log. Shows enable/disable events, re-engagements, completions. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair …
- `autopilot_progress` — Detailed task progress broken down by source (team-tasks, swarm-tasks, file-checklist). Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with…
- `autopilot_status` — Get autopilot state including enabled status, iteration count, task progress, and learning metrics. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop schedule…
- `browser_cookie_use` — Fetch a vault handle for a host from the browser-cookies AgentDB namespace. Raw cookie values are NEVER returned — only the opaque handle plus expiry / AIDefence verdict. Use when native WebFetch is wrong because you need real browser au…
- `browser_extract` — Extract structured data from the current page: text, links, a table, or an attribute across matching elements.
- `browser_get-text` — Get text content of an element Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content re…
- `browser_get-title` — Get the page title Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude…
- `browser_get-url` — Get the current URL Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claud…
- `browser_get-value` — Get value of an input element Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content rea…
- `browser_screenshot` — Capture a PNG of the current page as evidence. Returns the stored file path, not the raw bytes.
- `browser_session_replay` — Load a recorded session trajectory and return its steps so the caller can dispatch them through the 23 browser_* tools. Does NOT itself drive the browser — replay execution is caller-orchestrated to keep this tool a primitive (ADR-0001 §…
- `browser_session-list` — List active browser sessions Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reac…
- `browser_snapshot` — Accessibility-style snapshot of the current page: title, url, visible interactive elements with stable selectors, and page text wrapped as untrusted content.
- `business_pod_route_backend` — ADR-164 Phase 3 — Compute the domain-affinity routing decision for a business pod per ADR-164 §3.4 and return {backend, reason}. The three backends are local-stdio (preferLocalExecution=true), cloud-managed (preferLocalExecution=false AN…
- `business_pod_validate` — ADR-164 Phase 2 — Validate a business-pod template JSON against the schema in ADR-164 §3.3 (name, agents[], allowedMcpTools, bench, piiPolicy, budgets, cronSchedule, auditReadView, reservationExpiryMs bounded by ADR-164.1 §3.2). Use when…
- `channel_list` — Lists recently observed swarm channels with visibility, message count, publisher count, and purpose. Public channel ids contain their name (pub:<name>); private ids are opaque (prv:<hex>) and reveal no topic. Well-known public channels a…
- `channel_sync` — Read recent messages from a ruflo swarm channel (e.g. pub:announce, pub:help). Use before publishing, to see what has already been said and avoid duplicating it. Private (prv:) channels are returned as opaque ciphertext because this conn…
- `cite` — Generate citation
- `claims_board` — Get a visual board view of all claims Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For tr…
- `claims_list` — List all claims or filter by criteria Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For tr…
- `claims_load` — Get agent load information Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For trusted in-se…
- `claims_status` — Current owner-per-resource claims ledger from recent verified claim events. Open read.
- `claims_stealable` — List all stealable issues Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For trusted in-ses…
- `clean_leads` — Clean and dedupe emails from messy text or CSV (Automation Desk)
- `config_export` — Export configuration to JSON Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. F…
- `config_get` — Get configuration value Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .g…
- `config_list` — List configuration values Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For …
- `context_compact` — Local line dedupe retaining errors; not upstream Headroom / ضغط محلي
- `coordination_metrics` — Get coordination metrics Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task is fine.
- `cve_lookup` — Lookup CVE details
- `daa_learning_status` — Get learning status for DAA agents Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For static…
- `daa_performance_metrics` — Get DAA performance metrics Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For static one-sh…
- `demo_tool` — test
- `embeddings_compare` — Compare similarity between two texts Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector against your knowle…
- `embeddings_generate` — Generate embeddings for text (Euclidean or hyperbolic) Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector a…
- `embeddings_hyperbolic` — Hyperbolic embedding operations (Poincaré ball) Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector against …
- `embeddings_neural` — Neural substrate operations (RuVector integration) Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector again…
- `embeddings_rabitq_search` — Search via RaBitQ quantized index (fast Hamming scan). Returns candidate IDs for reranking. Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentd…
- `embeddings_rabitq_status` — Get RaBitQ quantized index status — availability, vector count, compression ratio Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-…
- `embeddings_search` — Semantic search across stored embeddings Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector against your kn…
- `embeddings_status` — Get embeddings system status and configuration Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector against y…
- `extract_contacts` — Extract emails, phones and social links from public HTML (Automation Desk)
- `features_detect` — Detect runtime features (V2 compatible). Deprecated: Use system/info instead.
- `federation_audit` — Query federation audit logs with optional compliance mode filtering
- `federation_bbs_identity` — agentbbs Phase 2 — return this host
- `federation_bbs_peers` — agentbbs Phase 2 — list pinned federation peers with last-sync state. Public keys are returned so an operator can compare a pin against what the peer reports; private material is never included. Use when you want to audit who this host w…
- `federation_bbs_sync` — agentbbs Phase 2 — pull a room from pinned peers and union-merge what verifies. Merge is keyed on envelopeId so it is idempotent and order-independent; unsigned, misattributed, oversize and over-hop (>${MAX_HOPS}) envelopes are dropped a…
- `federation_bbs_watch` — agentbbs — Poll recent envelopes from a BBS room (ADR-164 Phase 1). Returns envelopes newer than the optional sinceEnvelopeId, up to limit. Use when a pod agent needs to see incoming human overrides, new tasks, or peer events posted to i…
- `federation_breaker_status` — ADR-097 Phase 4: per-peer circuit-breaker state snapshot. Returns each known peer with its lifecycle state (ACTIVE/SUSPENDED/EVICTED), when it changed, and why. Combine with federation_evict / federation_reactivate to operate the breaker…
- `federation_evict` — ADR-097 Phase 4: operator-initiated evict for a peer. Marks the peer EVICTED so subsequent federation_send calls short-circuit with PEER_EVICTED. Reversible only via federation_reactivate (operator override).
- `federation_identity` — This connector\
- `federation_join` — Publishes a signed PeerHello using the gateway identity. Requires OAuth swarm:publish or the service-side admin token.
- `federation_onboarding` — Returns the public federation onboarding guide, including identity ownership, signing boundaries, enrollment steps, and local client commands. It never generates, receives, or requests a secret key.
- `federation_peers` — List all known federation peers with their trust levels and status
- `federation_query` — Query federated memory from a remote peer (PII-gated)
- `federation_reactivate` — ADR-097 Phase 4: operator-initiated reactivate for a SUSPENDED or EVICTED peer. Used after a health probe confirms recovery, or as an operator override on a manual evict. The breaker does NOT auto-reactivate; this MCP tool is the explici…
- `federation_status` — Get federation health status including active sessions, peers, and trust levels
- `federation_sync` — Fetch recent verified swarm coordination messages (#t=ruflo-swarm). Open read; optional type filter.
- `federation_trust` — View or review trust score details for a specific node
- `federation_wg_status` — ADR-111 Phase 6: WG mesh state — per-peer trust level, mesh IP, suspended/evicted flags, and the AllowedIPs slice each peer currently has. Use to inspect what the breaker has propagated to the L3 layer.
- `forge_detect` — Detect code-hosting forge for a URL
- `get_agent` — Use this to load one agent\
- `get-metrics` — Get collected metrics
- `git-status` — Get current Git repository status
- `github_metrics` — Get repository metrics and statistics Use when native Bash / file tools are wrong because this MCP tool exposes Ruflo-specific state or controllers that have no shell equivalent. For tasks that fit a one-line native command, prefer that.
- `github_repo_analyze` — Analyze a GitHub repository Use when native Bash / file tools are wrong because this MCP tool exposes Ruflo-specific state or controllers that have no shell equivalent. For tasks that fit a one-line native command, prefer that.
- `github_url_tricks` — Expand a GitHub repo URL into intelligence viewer/API links
- `grounded_query` — Query Google Search via Gemini 2.5 Flash grounding.
- `gt_agents` — List Gas Town agents with optional role and rig filters
- `gt_beads_ready` — List beads that are ready to work on (no unresolved dependencies)
- `gt_beads_show` — Show detailed information about a specific bead including dependencies
- `gt_convoy_status` — Check the status of one or all convoys including progress metrics
- `gt_formula_list` — List available Gas Town formulas with optional type filter
- `gt_wasm_match_pattern` — Find similar formulas or beads using HNSW pattern matching (150x-12500x faster)
- `guidance` — Get instructions on how to use the available tool groups and services. Call this FIRST when unsure which tool to use, when a user asks
- `guidance_brain` — Use when choosing how to execute a task with Ruflo. Queries the live capability brain, covers every registered MCP tool, separates registration from configuration/reachability/health/authorization, recommends capabilities, and returns th…
- `guidance_capabilities` — List all capability areas with their tools, commands, agents, and skills. Use this to discover what Ruflo can do. Use when generic
- `guidance_discover` — Discover all available agents and skills from the .claude/ directory. Returns live filesystem data. Use when generic
- `guidance_quickref` — Quick reference card for common operations. Returns the most useful commands for a given domain. Use when generic
- `guidance_recommend` — Given a task description, recommend which capability areas, tools, agents, and workflow to use. Use when generic
- `guidance_workflow` — Get a recommended workflow template for a task type. Includes steps, agents, and topology. Use when generic
- `hive-mind_memory` — Access hive shared memory Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagent, native …
- `hive-mind_status` — Get hive-mind status Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagent, native Task …
- `hooks_coverage-gaps` — List all coverage gaps with priority scoring and agent assignments
- `hooks_coverage-suggest` — Suggest coverage improvements for a path (ruvector integration)
- `hooks_explain` — Explain routing decision with full transparency Use when native Bash hooks (via Claude Code\
- `hooks_intelligence` — RuVector intelligence system status (shows REAL metrics from memory store) Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_pattern-search` — Search patterns using REAL vector search (HNSW when available, brute-force fallback) Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_stats` — Get RuVector intelligence layer statistics Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_unified-stats` — One honest view across the four learning stat sources: globalStats (
- `hooks_list` — List all registered hooks Use when native Bash hooks (via Claude Code\
- `hooks_metrics` — View learning metrics dashboard Use when native Bash hooks (via Claude Code\
- `hooks_model-stats` — Get model routing statistics Use when native Bash hooks (via Claude Code\
- `hooks_model-verify` — Verify a generated output with CHEAP structural signals ($0, no LLM call) and get an escalation verdict — the post-generation half of confidence-gated tier routing (route → generate → verify → escalate on failure). Checks: empty/truncate…
- `hooks_pre-edit` — Get context and agent suggestions before editing a file Use when native Bash hooks (via Claude Code\
- `hooks_route` — Get a 3-tier routing recommendation for a task: Tier 1 (deterministic codemod, ~0ms / $0 — for var-to-const, remove-console, add-logging), Tier 2 (Haiku — simple), Tier 3 (Sonnet/Opus — complex). Use this BEFORE spawning an agent to avoi…
- `hooks_session-end` — End current session, stop daemon, and persist state Use when native Bash hooks (via Claude Code\
- `hooks_worker-detect` — Detect worker triggers from user prompt (for UserPromptSubmit hook) Use when native Bash hooks (via Claude Code\
- `hooks_worker-list` — List all 12 background workers with status and capabilities Use when native Bash hooks (via Claude Code\
- `hooks_worker-status` — Get status of a specific worker or all active workers Use when native Bash hooks (via Claude Code\
- `html_extract_links` — Extract links from supplied HTML; no crawling / استخراج الروابط محلياً
- `hub_agent_audit` — Audit agents: responsibility, permitted tools, which of those tools passed an executed smoke check, inputs, outputs, model and API requirements, runtime dependencies, readiness and concrete limitations. Readiness is measured from execute…
- `hub_agent_browse` — Browse the Hub CATALOG: packs, all agents (with real capabilities and runtime readiness), tools13, MCP tools. Search by query or capability, or open one agent_id. For browsing actual websites use browser_navigate.
- `hub_edge_health` — Read public edge health; never uses a secret path
- `hub_freellmapi_status` — Probe FreeLLMAPI (open-source free LLM gateway) — /v1/models health, catalog sample, connection hints
- `hub_full_roster` — Return the complete agent directory that hub-boss knows (all packs)
- `hub_health` — Hub runtime/model/storage readiness (no secrets)
- `hub_integrations` — Integration readiness: provider identity, authentication requirement, operations, scopes, rate limits, quota, cost and health. Never returns credential values.
- `hub_list_agents` — List all agents across packs (optional pack filter)
- `hub_list_packs` — List Hub packs (hub, desk, ecc68, forge, tools13)
- `hub_tools13_lookup` — List or look up the 13 Hub Boss recovery tools
- `hyperbolic_hierarchy_compare` — Compare hierarchies using hyperbolic alignment. Computes structural and semantic similarity with node-level alignments.
- `hyperbolic_semantic_search` — Semantic search with hierarchical awareness. Supports nearest, subtree, ancestors, siblings, and cone search modes.
- `hyperbolic_taxonomic_reason` — Taxonomic reasoning using hyperbolic entailment. Supports IS-A, subsumption, LCA, path, and similarity queries.
- `iot_custody_epoch` — Get custody epoch
- `iot_device_list` — List all registered devices
- `iot_device_pair` — Pair with a registered device to establish mutual trust
- `iot_device_status` — Get device status and trust score
- `iot_firmware_rollout_list` — List firmware rollouts
- `iot_firmware_rollout_status` — Get firmware rollout status
- `iot_fleet_get` — Get fleet details
- `iot_fleet_list` — List all fleets
- `iot_fleet_status` — Get fleet overview
- `iot_mesh_topology` — Get mesh network topology
- `iot_store_query` — Query device vector store
- `iot_store_status` — Get vector store health
- `iot_telemetry_anomalies` — Detect anomalies in device telemetry readings
- `iot_telemetry_baseline` — Compute or retrieve telemetry baseline for a device
- `iot_witness_chain` — Get witness chain provenance
- `iot_witness_verify` — Verify witness chain integrity for a device — detects epoch gaps and hash chain breaks
- `list_categories` — Use this to show the 13 categories of the 243 expert agents and how many agents are in each.
- `list_files` — List all files in the virtual filesystem. No parameters needed. Returns file paths.
- `managed_agent_events` — Fetch the full server-persisted event log of a managed cloud-agent session (user turns, agent thinking, tool_use, tool_result, status) — the transcript/artifact view, the CLOUD counterpart of wasm_agent_files. Use when native Read is wro…
- `managed_agent_list` — List managed cloud-agent sessions on this Anthropic org (id, status, title) — the CLOUD counterpart of wasm_agent_list. Use when native conversation memory is wrong because you need to see which cloud sessions exist (and which are still …
- `managed_agent_status` — Get the lifecycle state of a managed cloud-agent session: idle/running/error, title, last error. Use when native conversation memory is wrong because you need the cloud session\
- `mcp_status` — Get MCP server status, including stdio mode detection Use when native Claude Code MCP status is wrong because you need Ruflo-side server detail — tool counts per namespace, transport stats, MCP handshake errors. For just
- `memory_bridge_status` — Show Claude Code memory bridge status — AgentDB vectors, SONA learning, intelligence patterns, and connection health. Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddi…
- `memory_list` — Enumerate stored memory entries (optionally filtered by namespace/tags) without semantic search. Use when native Glob is wrong because the entries are not files (they live in .swarm/memory.db). For inspection / audit /
- `memory_retrieve` — Read back a value previously stored via memory_store, by exact (namespace, key) — lossless, includes metadata. Use when native Read is wrong because the value is not a file (it lives in the .swarm/memory.db SQLite store) AND you know the…
- `memory_search` — Searches tenant-local team memory using a tenant-separated RuVector index when available, with an explicitly labelled lexical fallback. Requires team:read. Results are fenced as untrusted stored data.
- `memory_search_unified` — Search across both Claude Code memories and AgentDB entries using semantic vector similarity. Returns merged, deduplicated results from all namespaces. Use when native Read/Write is wrong because you need (a) cross-session retrieval by s…
- `memory_stats` — Get memory storage statistics including HNSW index status Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing across projects witho…
- `metaharness_audit_list` — ADR-150 iter 16 — list timestamped records from the
- `metaharness_audit_trend` — ADR-150 iter 15 — diff two oia-audit records (drift detection). Accepts EITHER memory keys (run metaharness_audit_list first to discover them) OR direct file paths (useful for diffing CI artifacts). Surfaces composite worst-severity delt…
- `metaharness_drift_from_history` — iter 53 — one-command drift detection. Composes audit-list + oia-audit + audit-trend: finds the most recent record in
- `metaharness_flywheel` — ADR-322 — evaluate candidates into immutable receipts, inspect the append-only promotion ledger, and explicitly promote one signed receipt with atomic compare-and-swap semantics. Use when running governed flywheel evaluation or promotion…
- `metaharness_genome` — ADR-150 — 7-section categorical readiness report from
- `metaharness_mcp_scan` — ADR-150 — static security scan of
- `metaharness_score` — ADR-150 — 5-dimension harness readiness scorecard from
- `metaharness_similarity` — ADR-152 §3.1 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall ∈ [0,1] plus per-component breakdown (cosine over 9 numerics, categorical over 4 enums, jaccard over agent_topology). Pure-TS, zero
- `metaharness_threat_model` — ADR-150 — enterprise-grade threat model from
- `n8n_workflow_validate` — Validate supplied workflow JSON without execution / تحقق دون تشغيل
- `neural_compress` — Compress neural model or embeddings Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Of…
- `neural_status` — Get neural system status Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-path for …
- `pattern_search` — Search patterns (HNSW)
- `performance_bottleneck` — Detect performance bottlenecks Use when native shell timing (
- `performance_metrics` — Get detailed performance metrics Use when native shell timing (
- `performance_report` — Generate performance report Use when native shell timing (
- `policy_status` — Inspect policy mode, migration state, rules, budgets, approvals, and ledger integrity. Use when diagnosing whether an installation is in compatibility, observation, or enforcement mode.
- `pr_coherence_check` — Check coherence of vectors using Sheaf Laplacian energy (0=coherent, 1=contradictory)
- `pr_consensus_verify` — Verify multi-agent consensus mathematically
- `pr_spectral_analyze` — Analyze stability using spectral graph theory
- `pre-browse` — Get recommendations before browser automation
- `progress_check` — Get current V3 implementation progress percentage and metrics Use when native TodoWrite is wrong because you need cross-session goal-completion tracking with witness/audit trail. For in-session checklists, native TodoWrite is simpler.
- `progress_summary` — Get human-readable V3 implementation progress summary Use when native TodoWrite is wrong because you need cross-session goal-completion tracking with witness/audit trail. For in-session checklists, native TodoWrite is simpler.
- `progress_watch` — Get current watch status for progress monitoring Use when native TodoWrite is wrong because you need cross-session goal-completion tracking with witness/audit trail. For in-session checklists, native TodoWrite is simpler.
- `read_file` — Read a file from the virtual filesystem (worker mock)
- `retrieve-reasoning` — Retrieve similar reasoning patterns
- `ruv_github_file` — Read one text file (up to 64 KiB) from a public repository of an allowlisted owner. Credential and key files such as .env, *.pem, *.key and id_rsa are refused. Results are third-party content.
- `ruv_github_repo` — Metadata for one public repository of an allowlisted owner: description, stars, language, license, latest release or tag, and optionally a README excerpt and the top-level file list. Results are third-party content.
- `ruv_github_search` — Search the public repositories, issues or code of an allowlisted GitHub owner (default ruvnet). Code search is available only when the gateway holds a server-side GitHub token. Results are third-party content.
- `ruv_registry_latest` — Latest published npm version of a package maintained by an allowlisted npm account (default ruvnet).
- `ruvector_health` — Check the health status of the RuVector connection and database.
- `ruvector_index_stats` — Get statistics for vector indices.
- `ruvector_metrics` — Get performance metrics and statistics.
- `ruvector_search` — Search for similar vectors using HNSW or IVF indexing. Supports cosine, euclidean, and dot product distance metrics.
- `ruvllm_chat_format` — Format chat messages using a template (llama3, mistral, chatml, phi, gemma, or auto-detect). Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per…
- `ruvllm_hnsw_route` — Route a query embedding to nearest patterns in HNSW index. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent per-ca…
- `ruvllm_status` — Get ruvllm-wasm availability and initialization status. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent per-call …
- `rvf_extract` — Extract RVF contents
- `rvf_verify` — Verify RVF container
- `scan-code` — Scan code for security vulnerabilities
- `search` — Search your knowledge base for relevant information.
- `search_agents` — Use this to find the best expert agent for a task. Searches agent ids, descriptions and instructions. Returns ids to pass to get_agent.
- `seo_audit_html` — Free Marketing SEO Audit on local HTML (tools13) — no Okara, no posting
- `session_info` — Get detailed session information Use when native conversation memory is wrong because you need durable cross-session state — restoring agent definitions, swarm topology, memory store, breaker history. For in-session continuation only, no…
- `session_list` — List saved sessions Use when native conversation memory is wrong because you need durable cross-session state — restoring agent definitions, swarm topology, memory store, breaker history. For in-session continuation only, no tool needed.…
- `sheets_to_json` — Convert CSV/TSV spreadsheet text to JSON rows (Automation Desk)
- `swarm_health` — Check swarm health status with real state inspection Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace…
- `swarm_monitor` — Monitor swarm activity (V2 compatible). Deprecated: Use swarm/status with includeMetrics instead.
- `swarm_pheromone_status` — Inspect the threshold, safety configuration, per-agent EMA scores, and scheduling eligibility of the active pheromone-adaptive swarm. Use when aggregate swarm status is wrong because calibration requires the exact APSC threshold and per-…
- `swarm_status` — Get swarm status from persistent state Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace, or anti-drif…
- `system_health` — Perform system health check Use when native Bash is wrong because you need Ruflo runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status) — those are not in /proc, only in the running daemon. For OS-level info…
- `system_info` — Get system information Use when native Bash is wrong because you need Ruflo runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status) — those are not in /proc, only in the running daemon. For OS-level info (upt…
- `system_metrics` — Get system metrics and performance data Use when native Bash is wrong because you need Ruflo runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status) — those are not in /proc, only in the running daemon. For O…
- `system_status` — Get overall system status Use when native Bash is wrong because you need Ruflo runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status) — those are not in /proc, only in the running daemon. For OS-level info (…
- `task_list` — Lists tasks for a tenant-local run. Requires team:read. Stored task text is returned as provenance-labelled untrusted data.
- `task_result` — Get task output/evidence/artifacts
- `task_results` — Retrieve results from completed tasks (V2 compatible). Deprecated: Use tasks/results instead.
- `task_status` — Get task status/progress
- `task_summary` — Get a summary of all tasks by status Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists na…
- `team_board` — Opens one private, read-only ChatGPT workspace for teams, runs, tasks, and evidence summaries. Requires team:read. The user can navigate and refresh inside this one widget; avoid calling it repeatedly in the same chat. No actions are exe…
- `team_get` — Reads one AI team owned by the authenticated tenant. Requires team:read. Foreign and missing IDs both return not_found.
- `team_list` — Lists AI teams owned by the authenticated tenant. Requires team:read. Returns no other tenant data.
- `team_templates_list` — Lists first-party AI-team playbooks and their roles. Requires team:read. Does not create or run a team.
- `teammate_delegate` — Delegate authority/permissions to another teammate
- `teammate_discover_teams` — Discover existing teams in ~/.claude/teams/
- `teammate_find_optimal_path` — Find optimal message routing path between two teammates using BMSSP graph algorithms.
- `teammate_get_status` — Get team and teammate status
- `teammate_get_topology_stats` — Get topology statistics and optimization suggestions for a team.
- `terminal_history` — Get command history for a terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine.
- `terminal_list` — List all terminal sessions Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine.
- `todo_list` — List all pending tasks
- `transfer_detect-pii` — Detect PII in content without redacting Use when native package install (
- `transfer_ipfs-resolve` — Resolve IPNS name to CID Use when native package install (
- `transfer_plugin-featured` — Get featured plugins from the store Use when native package install (
- `transfer_plugin-info` — Get detailed info about a plugin Use when native package install (
- `transfer_plugin-official` — Get official plugins from the store Use when native package install (
- `transfer_plugin-search` — Search the plugin store Use when native package install (
- `transfer_store-download` — Download a pattern from the store Use when native package install (
- `transfer_store-featured` — Get featured patterns from the store Use when native package install (
- `transfer_store-info` — Get detailed info about a pattern Use when native package install (
- `transfer_store-search` — Search the pattern store Use when native package install (
- `transfer_store-trending` — Get trending patterns from the store Use when native package install (
- `wasm_agent_export` — Export a WASM agent\
- `wasm_agent_files` — Get a WASM agent\
- `wasm_agent_is_stopped` — Check whether a WASM agent has reached its stop condition (max turns or explicit stop). Use when native Task is wrong because the stop condition is evaluated inside the WASM runtime and not observable from the host without an explicit qu…
- `wasm_agent_list` — List all active WASM agents. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, deterministic replay. Pair with wasm_gallery_search to find a published agent, or was…
- `wasm_agent_state` — Read the full internal state of a WASM agent (messages, turn count, config, stop status). Use when native Task is wrong because the agent runs in a sandboxed WASM runtime whose internal conversation history is not directly accessible fro…
- `wasm_agent_todos` — Get the structured todo list of a WASM agent as JSON. Use when native Task is wrong because the todo state lives inside the sandboxed WASM runtime and is not visible to the host process.
- `wasm_agent_tools` — List the tools registered on a WASM agent sandbox. Use when native Task is wrong because the tool registry lives inside the WASM runtime and cannot be inspected from the host via standard reflection.
- `wasm_agent_turn_count` — Return the current turn count of a WASM agent. Use when native Task is wrong because turn-limit enforcement and progress tracking must be polled from inside the sandboxed WASM runtime rather than inferred externally.
- `wasm_gallery_active` — Return the ID of the currently active WASM gallery template. Use when native Bash is wrong because the active-template cursor is tracked inside the WASM runtime state, not in a file you can read directly.
- `wasm_gallery_categories` — Return all WASM gallery template categories with per-category template counts. Use when native Bash/ls is wrong because gallery category metadata is indexed inside the WASM runtime, not on the filesystem.
- `wasm_gallery_config` — Get the runtime configuration overrides applied to the active WASM gallery template. Use when native Read is wrong because gallery config overrides are stored in the WASM runtime state rather than as an editable config file.
- `wasm_gallery_export` — Export all custom WASM gallery templates as a JSON snapshot. Use when native Read/cat is wrong because custom templates live inside the WASM runtime store and are not persisted as individual files on disk.
- `wasm_gallery_list` — List all available WASM agent gallery templates (Coder, Researcher, Tester, Reviewer, Security, Swarm). Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, determinis…
- `wasm_gallery_list_by_category` — List WASM gallery templates filtered to a specific category. Use when native Glob is wrong because gallery templates are stored in the WASM runtime registry, not as individual filesystem files.
- `wasm_gallery_load_rvf` — Load a named gallery template as a base64-encoded RVF container. Use when native Read is wrong because RVF containers are packed inside the WASM gallery store and are not accessible as plain filesystem files.
- `wasm_gallery_search` — Search WASM agent gallery templates by query. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, deterministic replay. Pair with wasm_gallery_search to find a publis…
- `web_research` — Search the web, fact-check claims, compare items, or conduct deep research. Actions:
- `web_search` — Search the web through a configured research integration (Tavily, Brave, Exa). Returns results with source URLs. Reports BLOCKED with the exact credential to set when no provider is configured — it never invents results.
- `witness_export` — Export chain for external audit
- `witness_verify` — Verify chain integrity
- `workflow_list` — List all workflows Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single linear…
- `workflow_status` — Get workflow status Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single linea…
- `x_federation_channel_list` — List the private channels this machine holds keys for, plus their local labels. Use when you want to know what you can actually read before calling channel_read. The gateway channel_list is the wrong tool for that: it reports channels se…
- `x_federation_channel_read` — Read a channel and decrypt what your keys can open. Public messages come back as JSON; private ones are decrypted locally with the cached channel key, and anything you have no key for is returned as encrypted:true rather than silently dr…
- `x_federation_claims` — Return the current owner-per-resource work-claims ledger for the open swarm (ruv://claims/board). Use when you are about to start shared work and need to know whether a resourceId is already owned. Inferring ownership from raw ClaimIssue…
- `x_federation_join` — Join the federation with YOUR OWN local key, without an invite when public registration is enabled. Reuses ~/.ruflo/nostr.key (0600), proves key ownership with NIP-98, and verifies membership with NIP-42. Use when a user wants to join as…
- `x_federation_registry` — Read the federation registry resource (ruv://federation/registry): relay URL, canonical relay tag for NIP-42, gateway pubkey, and the exact self-join steps. Use when onboarding a new node or user to the open federation. Hard-coding the r…
- `x_federation_roster` — List nodes currently announcing themselves on the open swarm (recent PeerHello events) via the ruv://swarm/roster resource. Use when you need to know who is online across the federation before assigning work. Grepping sync output by hand…
- `x_federation_sync` — Fetch recent signature-verified coordination messages from the open x.ruv.io swarm federation (Nostr, #t=ruflo-swarm). Use when you need to see what other ruflo nodes across the internet have posted (PeerHello/Status/Task/Result/Claim*).…
- `agent_update` — Mutate a tracked agent\
- `agentdb_causal-edge` — Record a causal edge between two memory entries via CausalMemoryGraph Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/reca…
- `agentdb_feedback` — Record task feedback for learning via LearningSystem + ReasoningBank controllers Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern…
- `agentdb_hierarchical-store` — Store to hierarchical memory with tier (working, episodic, semantic) Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recal…
- `agentdb_pattern-store` — Store a pattern directly via ReasoningBank controller Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall, RaBitQ quant…
- `agentdb_session-end` — End session, persist to ReflexionMemory, trigger NightlyLearner consolidation Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern st…
- `agenticow_branch` — agenticow@~0.2.3 — COW-fork a base .rvf memory file. Measured 162-byte branches regardless of base size (verified at N=1k/10k/50k). Use when you need per-Darwin-iteration / per-user / per-session memory personalization. Copying the paren…
- `agenticow_checkpoint` — agenticow — freeze a labelled restore point on an .rvf memory file. Subsequent edits stay in a fresh COW child; rollback returns here. Use when you are about to run an experimental Darwin tick or speculative agent edit that may need to b…
- `agenticow_ingest` — agenticow — write vectors (with optional text payloads) into an .rvf memory branch or base. Records: [{id?, vector, text?}] — id auto-assigns when omitted. This is the write half that makes a branch usable: agenticow_branch creates an em…
- `agenticow_promote` — agenticow — merge a branch\
- `aidefence_learn` — Record detection feedback for pattern learning. Improves future detection accuracy. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted…
- `autopilot_config` — Configure autopilot limits: max iterations (1-1000), timeout in minutes (1-1440), and task sources. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop schedule…
- `browser_act` — Perform one page action (click, type, select, press, scroll, upload). Prefer semantic targets (role+name, label, placeholder) over positions. Pass expect_text/expect_selector to get a verified outcome rather than
- `browser_session` — Manage real Chromium browser sessions (Playwright, CPU-only): status, open with a domain allow list, list, close, save an authorised login profile.
- `channel_publish` — Sign a message with this connector\
- `claims_claim` — Claim an issue for work (human or agent) Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For…
- `claims_issue` — Issue a work claim AS THE GATEWAY. Authorised by OAuth swarm:publish or the service-side admin token. One owner per resourceId.
- `claims_mark-stealable` — Mark an issue as stealable by other agents Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. F…
- `claims_release` — Release a gateway-held work claim. Authorised by OAuth swarm:publish or the service-side admin token.
- `config_import` — Import configuration from JSON Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json.…
- `config_set` — Set configuration value Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .g…
- `coordination_topology` — Configure swarm topology Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task is fine.
- `create-workflow` — Create a new workflow
- `daa_knowledge_share` — Share knowledge between agents Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For static one…
- `daa_workflow_create` — Create an autonomous workflow Use when native Task is wrong because you need agents that adapt their cognitive pattern (convergent / divergent / lateral / systems / critical) per-task and share knowledge across the swarm. For static one-…
- `evidence_export` — Builds a read-only evidence bundle for one tenant-local run, including team metadata, tasks, and privacy-minimized audit events. Requires team:read. It does not publish or share the bundle.
- `federation_admit` — Admit a pubkey as a relay member directly (NIP-43 kind 9030). Requires the admin token; OAuth swarm:publish is not sufficient.
- `federation_bbs_human_join` — agentbbs — Mint a single-use Ed25519-signed token a human business owner presents to the agentbbs SSH/web front door to join a room (ADR-164 §3.2.4). Returns webUrl + sshCommand + handshakeToken + expiresAt. Use when the cockpit operator…
- `federation_bbs_publish` — agentbbs — Publish a domain event from a pod agent to a BBS room (ADR-164 Phase 1). Wraps the payload in a ReplicateMessage envelope (envelopeId, seq, ts, msgType, payload) and appends it to the room log. Use when an agent has produced a…
- `federation_invite_mint` — Mint a self-service invite code so a new ruflo user can claim relay membership with their own key. Requires the admin token; OAuth swarm:publish is not sufficient.
- `federation_publish` — Publish a signed coordination message AS THE GATEWAY (Status/Task/Result…). Authorised by OAuth swarm:publish or the service-side admin token.
- `federation_wg_attest` — ADR-111 Phase 6 (witness chain): emit an operator-signed attestation entry for a coordination change. Returns the canonical bytes the operator signs + the witness entry; operator appends it to .claude-flow/federation/wg-changes.log. Idem…
- `feedback_record` — Record feedback for learning
- `git-commit` — Create a Git commit
- `github_issue_track` — Track and manage issues Use when native Bash / file tools are wrong because this MCP tool exposes Ruflo-specific state or controllers that have no shell equivalent. For tasks that fit a one-line native command, prefer that.
- `github_pr_manage` — Manage pull requests Use when native Bash / file tools are wrong because this MCP tool exposes Ruflo-specific state or controllers that have no shell equivalent. For tasks that fit a one-line native command, prefer that.
- `gt_beads_create` — Create a bead (issue/task) in the Gas Town Beads system with priority and labels
- `gt_beads_dep` — Add or remove dependencies between beads
- `gt_beads_sync` — Synchronize beads between Gas Town and Claude Flow AgentDB
- `gt_convoy_create` — Create a convoy (work order) for tracking and coordinating multiple beads
- `gt_convoy_track` — Add or remove issues from an existing convoy
- `gt_formula_create` — Create a custom formula definition
- `gt_mail` — Send, read, or list Gas Town internal mail messages
- `gt_sling` — Sling (assign) a bead to a Gas Town agent for processing
- `hive-mind_leave` — Remove an agent from the hive-mind Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a single subagent…
- `hive-mind_shutdown` — Shutdown the hive-mind and terminate all workers Use when native Task is wrong because you need queen-led collective intelligence — Byzantine-FT consensus, broadcast across many worker agents, shared memory with bounded conflict. For a s…
- `hooks_init` — Initialize hooks in project with .claude/settings.json Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_pattern-store` — Store pattern in ReasoningBank (HNSW-indexed) Use when native Bash hooks (via Claude Code\
- `hooks_intelligence_trajectory-step` — Record step in trajectory for reinforcement learning Use when native Bash hooks (via Claude Code\
- `hooks_model-outcome` — Record model routing outcome for learning Use when native Bash hooks (via Claude Code\
- `hooks_post-command` — Record command execution outcome Use when native Bash hooks (via Claude Code\
- `hooks_post-edit` — Record editing outcome for learning Use when native Bash hooks (via Claude Code\
- `hooks_post-task` — Record task completion for learning Use when native Bash hooks (via Claude Code\
- `hooks_session-restore` — Restore a previous session Use when native Bash hooks (via Claude Code\
- `hooks_task-completed` — Agent Teams hook — fired when a task is marked complete. Records the completion and, when
- `hub_boss_route` — Preview how hub-boss would differentiate and assign a mission using FULL roster awareness
- `hub_freellmapi_chat` — Send a one-shot chat completion through FreeLLMAPI (model=auto by default). Lab only — free tiers.
- `hub_tools13_capabilities` — Honest local runner availability and blocked install hints / حالة الأدوات
- `iot_device_register` — Register a Cognitum Seed device by endpoint
- `iot_firmware_rollout_create` — Create a firmware rollout for a fleet
- `iot_fleet_add_device` — Add a registered device to a fleet
- `iot_fleet_create` — Create a new device fleet
- `iot_store_ingest` — Ingest vectors into device store
- `memory_import_claude` — Import Claude Code auto-memory files into AgentDB with ONNX vector embeddings. Reads ~/.claude/projects/*/memory/*.md files, parses YAML frontmatter, splits into sections, and stores with 384-dim embeddings for semantic search. Use allPr…
- `memory_migrate` — Manually trigger migration from legacy JSON store to sql.js Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing across projects wit…
- `memory_remember` — Stores approved tenant-local team context for later vector retrieval. Requires team:write. Content is safety-scanned, isolated to the OAuth tenant, and never used for cross-tenant learning.
- `memory_store` — Store information in semantic memory
- `memory_usage` — Manage coordination memory (V2 compatible). Deprecated: Use memory/store, memory/search, or memory/list instead.
- `metaharness_bench` — ADR-153 supporting verb — create or verify bench suites used by metaharness_evolve --bench. Bench suites are JSON files of {input, expectedOutput, weight} tasks; scoring against a fixed corpus decouples evolution from flaky/slow/undersized
- `metaharness_oia_audit` — ADR-150 — composite weekly audit. Bundles oia-manifest + threat-model + mcp-scan into one timestamped record persisted to
- `neural_patterns` — Get or manage neural patterns Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-path…
- `pattern_store` — Store learned pattern
- `policy_budget_set` — Create or update an atomic USD/token ceiling for a principal, action, and resource window. Use when constraining agent spend; budget checks and decision receipts commit under the same policy-state lock.
- `policy_rule_upsert` — Create or update a versioned agentic policy rule. Use when defining explicit allow, deny, or human-approval requirements; existing installations remain unchanged until rules and enforcement mode are configured.
- `post-browse` — Record browser automation outcome for learning
- `pr_memory_gate` — Pre-storage coherence gate for memory entries
- `progress_sync` — Calculate and persist V3 progress metrics to file Use when native TodoWrite is wrong because you need cross-session goal-completion tracking with witness/audit trail. For in-session checklists, native TodoWrite is simpler.
- `report_vuln` — Generate vulnerability report
- `results_merge` — Merge results with CRDT
- `run_complete` — Marks a tenant-local coordination run complete only when it has at least one task and every task is complete. Requires team:run. Does not execute agents or external actions.
- `run_create` — Creates a budgeted coordination run for an existing team. Requires team:run. This records the run but does not contact external systems or spend provider credits.
- `ruvector_create_index` — Create a vector index (HNSW or IVF) for faster similarity search.
- `ruvector_insert` — Insert vectors into a table. Supports batch insertion and upsert.
- `ruvector_update` — Update an existing vector and/or its metadata.
- `ruvllm_generate_config` — Create a generation config (maxTokens, temperature, topP, etc.) as JSON. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or s…
- `ruvllm_hnsw_add` — Add a pattern to an HNSW router. Embedding must match router dimensions. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or s…
- `ruvllm_hnsw_create` — Create a WASM HNSW router for semantic pattern routing. Max ~11 patterns (v2.0.1 limit). Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-tas…
- `ruvllm_microlora_create` — Create a MicroLoRA adapter (ultra-lightweight LoRA, ranks 1-4). Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent p…
- `ruvllm_sona_create` — Create a SONA instant adaptation loop (<1ms adaptation cycles). Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent p…
- `session_restore` — Restore a saved session Use when native conversation memory is wrong because you need durable cross-session state — restoring agent definitions, swarm topology, memory store, breaker history. For in-session continuation only, no tool nee…
- `session_save` — Save current session state Use when native conversation memory is wrong because you need durable cross-session state — restoring agent definitions, swarm topology, memory store, breaker history. For in-session continuation only, no tool …
- `store-reasoning` — Store a reasoning pattern
- `swarm_pheromone_update` — Record a normalized per-agent task outcome for a running pheromone-adaptive swarm. Use when a static agent pool is wrong because repeated task evidence should update role-aware EMA fitness and produce a bounded keep/suspend/reactivate de…
- `swarm_shutdown` — Shutdown a swarm and update persistent state Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace, or ant…
- `task_complete` — Mark task as complete Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite …
- `task_create` — Adds a bounded task to a tenant-local run. Requires team:write. It records coordination state only and does not execute the task.
- `task_update` — Updates status or result for a tenant-local task. Requires team:write. It cannot execute commands, publish messages, or approve external actions.
- `team_create` — Creates a tenant-local AI-team record from a reviewed goal and optional playbook. Requires team:write. Does not start agents, contact external services, or incur model charges.
- `team_update` — Updates the name, objective, roles, or status of an existing tenant-local team. Requires team:write. It does not run agents or perform external actions.
- `teammate_broadcast` — Broadcast message to all teammates in a team
- `teammate_save_memory` — Save teammate session memory to disk
- `teammate_send_message` — Send a message to a specific teammate
- `teammate_share_transcript` — Share message transcript with another teammate
- `teammate_spawn_team` — Create a new team for multi-agent collaboration using native TeammateTool.
- `teammate_submit_plan` — Submit a plan for team approval
- `teammate_update_context` — Update team shared context
- `terminal_close` — Close a terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine.
- `todo_add` — Add a task to the todo list
- `todo_complete` — Mark a task as complete
- `wasm_agent_terminate` — Terminate a WASM agent and free resources. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, deterministic replay. Pair with wasm_gallery_search to find a published…
- `wasm_gallery_add_custom` — Add a custom agent template to the WASM gallery registry. Use when native Write is wrong because custom templates must be registered inside the WASM runtime store, not written as plain files.
- `wasm_gallery_configure` — Apply runtime configuration overrides (e.g. maxTurns, model) to the active WASM gallery template. Use when native Edit is wrong because gallery configuration lives inside the WASM runtime state and cannot be changed via filesystem writes.
- `witness_append` — Append to witness chain
- `witness_log` — Log to witness chain (immutable audit)
- `workflow_create` — Create a new workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single lin…
- `workflow_template` — Save workflow as template or create from template Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-dr…
- `write_file` — Write a file to the virtual filesystem (worker mock)
- `x_federation_admit` — Admit a Nostr pubkey as a relay member directly (NIP-43 kind 9030). Requires RUFLO_X_ADMIN_TOKEN. Use when a known node reports its 64-hex pubkey and you want to skip the invite step. Padding or hand-editing a reported pubkey is wrong be…
- `x_federation_channel_accept` — Accept private-channel grants addressed to your key: finds ChannelGrant events tagged to your pubkey, opens each with your own secret key, and caches the channel keys locally. Use when someone tells you they granted you a channel. Asking…
- `x_federation_channel_create` — Create a swarm channel. visibility=public gives a named stream every relay member can read (pub:<name>). visibility=private generates a 32-byte key HERE, stores it at ~/.ruflo/channels.json (0600), and returns an opaque id (prv:<hex>) th…
- `x_federation_channel_grant` — Grant a member access to a private channel by sealing its key to their pubkey with NIP-44 (ECDH), published as a ChannelGrant event only they can open. Use when adding a participant to an existing private channel. Publishing the raw key …
- `x_federation_channel_publish` — Publish a message to a channel with YOUR OWN key. A private channel is encrypted locally under its channel key before it leaves this machine, and the message type is hidden behind k=enc so the relay sees only an opaque id and ciphertext.…
- `x_federation_invite_mint` — Mint a use-limited, expiring invite code so a new ruflo user can self-join the open federation with THEIR OWN key. Requires RUFLO_X_ADMIN_TOKEN. Use when onboarding someone. Sharing the relay owner key instead is wrong because invites ar…
- `x_federation_publish` — Publish a signed coordination message to the open swarm AS THE GATEWAY identity (Status/Task/Result/…). Requires RUFLO_X_ADMIN_TOKEN. Use when a trusted operator needs a hub-level broadcast. Using this to post on behalf of an individual …

## Related servers

- Delx Mcp A2a (1068 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md
- Hermoso (896 tools) — https://policylayer.com/tools/hermoso.md
- Ainumbers Mcp Apps (745 tools) — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps.md
- Delx MCP Server (740 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-server.md
- Binance MCP Server (734 tools) — https://policylayer.com/tools/nirholas-binance-mcp.md
- Nitrostack (697 tools) — https://policylayer.com/tools/nitrostack.md
- Yaver (678 tools) — https://policylayer.com/tools/io-github-kivanccakmak-yaver.md
- Vibecontrols (672 tools) — https://policylayer.com/tools/vibecontrols-mcp.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=hamza-agent-hub-252 · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/hamza-agent-hub-252