# Todo for AI MCP Server MCP server Agent View of the PolicyLayer registry record for Todo for AI MCP Server: identity, probed posture, risk grade, and all 244 tools classified. HTML page: https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp ## Facts - Server id: `todo-for-ai/todo-for-ai-mcp` - Homepage: https://github.com/todo-for-ai/todo-for-ai-mcp - Registry record: grade F, identity unverified - Lifecycle: active - Rate-limited: no - Tools: 244 - Tool categories present: Destructive, Execute, Read, Write - Tags: todo for ai todo for ai mcp, admin, automation - Record last modified: 2026-09-03T05:08:49.819Z ## Tools (244) | Tool | Category | Risk | Record | | --- | --- | --- | --- | | `cancel_workflow_run` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/cancel-workflow-run.md | | `clear_step_runtime_override` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/clear-step-runtime-override.md | | `delete_agent_experience` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-agent-experience.md | | `delete_collaboration_template` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-collaboration-template.md | | `delete_knowledge_entry` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-knowledge-entry.md | | `delete_sandbox` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-sandbox.md | | `delete_shared_context` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-shared-context.md | | `delete_workflow` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-workflow.md | | `delete_workflow_trigger` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-workflow-trigger.md | | `revoke_cross_project_agent` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/revoke-cross-project-agent.md | | `revoke_sandbox_execution` | Destructive | Critical | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/revoke-sandbox-execution.md | | `append_run_logs` | Execute | High | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/append-run-logs.md | | `escalate_overdue_tasks` | Execute | High | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/escalate-overdue-tasks.md | | `handoff_task` | Execute | High | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/handoff-task.md | | `launch_workflow` | Execute | High | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/launch-workflow.md | | `pause_workflow_run` | Execute | High | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/pause-workflow-run.md | | `retry_workflow_run` | Execute | High | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/retry-workflow-run.md | | `start_sandbox_execution` | Execute | High | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/start-sandbox-execution.md | | `acknowledge_conflict` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/acknowledge-conflict.md | | `authorize_cross_project_agent` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/authorize-cross-project-agent.md | | `auto_extract_experiences` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/auto-extract-experiences.md | | `auto_extract_knowledge` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/auto-extract-knowledge.md | | `bind_agent_sandbox` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/bind-agent-sandbox.md | | `check_sandbox_action` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/check-sandbox-action.md | | `claim_agent_task` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/claim-agent-task.md | | `claim_cross_project_task` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/claim-cross-project-task.md | | `collaboration_graph` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/collaboration-graph.md | | `collaboration_metrics` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/collaboration-metrics.md | | `decay_all_experiences` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/decay-all-experiences.md | | `diff_workflow_versions` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/diff-workflow-versions.md | | `discover_agents` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/discover-agents.md | | `discover_cross_project_agents` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/discover-cross-project-agents.md | | `dispatch_tasks` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/dispatch-tasks.md | | `find_capable_agents_cross_project` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/find-capable-agents-cross-project.md | | `find_cross_project_tasks` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/find-cross-project-tasks.md | | `fire_due_triggers` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/fire-due-triggers.md | | `get_agent_capability_gap_analysis` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-capability-gap-analysis.md | | `get_agent_capability_supply_demand` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-capability-supply-demand.md | | `get_agent_collaborators` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-collaborators.md | | `get_agent_cross_project_efficiency` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-cross-project-efficiency.md | | `get_agent_experience` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-experience.md | | `get_agent_experiences_decay_alerts` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-experiences-decay-alerts.md | | `get_agent_failure_error_patterns` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-failure-error-patterns.md | | `get_agent_failure_reasons` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-failure-reasons.md | | `get_agent_health` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-health.md | | `get_agent_health_alerts` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-health-alerts.md | | `get_agent_health_state_transitions` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-health-state-transitions.md | | `get_agent_health_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-health-trend.md | | `get_agent_idle_ranking` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-idle-ranking.md | | `get_agent_inbox` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-inbox.md | | `get_agent_messages` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-messages.md | | `get_agent_productivity` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-productivity.md | | `get_agent_productivity_alerts` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-productivity-alerts.md | | `get_agent_productivity_by_kind` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-productivity-by-kind.md | | `get_agent_productivity_calendar_heatmap` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-productivity-calendar-heatmap.md | | `get_agent_productivity_hourly_heatmap` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-productivity-hourly-heatmap.md | | `get_agent_productivity_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-productivity-trend.md | | `get_agent_productivity_weekly_comparison` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-productivity-weekly-comparison.md | | `get_agent_reputation` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-reputation.md | | `get_agent_reputation_history` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-reputation-history.md | | `get_agent_run_resource_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-run-resource-trend.md | | `get_agent_run_resource_usage` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-run-resource-usage.md | | `get_agent_sandbox` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-sandbox.md | | `get_agent_skill_matching` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-skill-matching.md | | `get_agent_specialization_evolution` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-specialization-evolution.md | | `get_agent_task_handoff_stats` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-task-handoff-stats.md | | `get_agent_workload_forecast` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-workload-forecast.md | | `get_channel_activity_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-channel-activity-trend.md | | `get_collaboration_graph_timeline` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-collaboration-graph-timeline.md | | `get_conflict` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-conflict.md | | `get_conflicts_by_agent` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-conflicts-by-agent.md | | `get_conflicts_dashboard` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-conflicts-dashboard.md | | `get_conflicts_sandbox_correlation` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-conflicts-sandbox-correlation.md | | `get_conflicts_strategy_stats` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-conflicts-strategy-stats.md | | `get_conflicts_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-conflicts-trend.md | | `get_experience_validation_stats` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experience-validation-stats.md | | `get_experiences_confidence_decay_forecast` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-confidence-decay-forecast.md | | `get_experiences_confidence_distribution` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-confidence-distribution.md | | `get_experiences_decay_by_domain` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-decay-by-domain.md | | `get_experiences_decay_by_task_type` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-decay-by-task-type.md | | `get_experiences_low_confidence` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-low-confidence.md | | `get_experiences_propagation_chain` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-propagation-chain.md | | `get_experiences_reuse_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-reuse-trend.md | | `get_experiences_scatter` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-scatter.md | | `get_experiences_skill_coverage_radar` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-skill-coverage-radar.md | | `get_experiences_source_distribution` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-source-distribution.md | | `get_experiences_stats` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-experiences-stats.md | | `get_knowledge_entry` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-knowledge-entry.md | | `get_knowledge_propagation_network` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-knowledge-propagation-network.md | | `get_orchestrator_status` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-orchestrator-status.md | | `get_project_info` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-project-info.md | | `get_project_tasks_by_name` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-project-tasks-by-name.md | | `get_protocol` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-protocol.md | | `get_protocol_analytics` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-protocol-analytics.md | | `get_protocol_decision_latency` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-protocol-decision-latency.md | | `get_run_logs` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-run-logs.md | | `get_sandbox` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-sandbox.md | | `get_sandbox_dashboard` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-sandbox-dashboard.md | | `get_sandbox_execution` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-sandbox-execution.md | | `get_sandbox_template_usage` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-sandbox-template-usage.md | | `get_sandbox_violation_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-sandbox-violation-trend.md | | `get_sandbox_violations_by_agent` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-sandbox-violations-by-agent.md | | `get_shared_context` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-shared-context.md | | `get_step_effective_params` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-step-effective-params.md | | `get_step_sandbox_execution` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-step-sandbox-execution.md | | `get_task_allocation_fairness` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-allocation-fairness.md | | `get_task_by_id` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-by-id.md | | `get_task_comment_sentiment_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-comment-sentiment-trend.md | | `get_task_completion_by_assignee` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-completion-by-assignee.md | | `get_task_completion_by_priority` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-completion-by-priority.md | | `get_task_completion_by_project` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-completion-by-project.md | | `get_task_completion_forecast` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-completion-forecast.md | | `get_task_completion_rate_by_project` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-completion-rate-by-project.md | | `get_task_dependency_chain` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-dependency-chain.md | | `get_task_evidence` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-evidence.md | | `get_task_overdue_by_assignee` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-overdue-by-assignee.md | | `get_task_overdue_clustering` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-overdue-clustering.md | | `get_task_overdue_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-overdue-trend.md | | `get_task_priority_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-priority-trend.md | | `get_task_rework_analysis` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-rework-analysis.md | | `get_task_stats` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-task-stats.md | | `get_workflow` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow.md | | `get_workflow_failed_steps_by_duration` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-failed-steps-by-duration.md | | `get_workflow_failure_correlation` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-failure-correlation.md | | `get_workflow_failure_correlation_by_step` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-failure-correlation-by-step.md | | `get_workflow_run` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-run.md | | `get_workflow_run_console` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-run-console.md | | `get_workflow_run_duration_percentiles` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-run-duration-percentiles.md | | `get_workflow_run_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-run-trend.md | | `get_workflow_similarity_matrix` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-similarity-matrix.md | | `get_workflow_step_bottleneck_timeline` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-bottleneck-timeline.md | | `get_workflow_step_cofailure_matrix` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-cofailure-matrix.md | | `get_workflow_step_dependency_bottleneck` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-dependency-bottleneck.md | | `get_workflow_step_duration_histogram` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-duration-histogram.md | | `get_workflow_step_failure_rate` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-failure-rate.md | | `get_workflow_step_hourly_distribution` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-hourly-distribution.md | | `get_workflow_step_retry_topology` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-retry-topology.md | | `get_workflow_step_stats` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-step-stats.md | | `get_workflow_structural_complexity` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-structural-complexity.md | | `get_workflow_success_rate_by_workflow` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-success-rate-by-workflow.md | | `get_workflow_template` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-template.md | | `get_workflow_version` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-workflow-version.md | | `health_check` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/health-check.md | | `ignore_conflict` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/ignore-conflict.md | | `instantiate_collaboration_template` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/instantiate-collaboration-template.md | | `learn_from_experience` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/learn-from-experience.md | | `list_agent_assignments` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-agent-assignments.md | | `list_agent_cross_projects` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-agent-cross-projects.md | | `list_agent_experiences` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-agent-experiences.md | | `list_agents` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-agents.md | | `list_audit_logs` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-audit-logs.md | | `list_channel_messages` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-channel-messages.md | | `list_channels` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-channels.md | | `list_collaboration_templates` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-collaboration-templates.md | | `list_conflicts` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-conflicts.md | | `list_knowledge_entries` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-knowledge-entries.md | | `list_my_tasks` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-my-tasks.md | | `list_notifications` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-notifications.md | | `list_orchestrator_history` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-orchestrator-history.md | | `list_project_external_agents` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-project-external-agents.md | | `list_protocols` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-protocols.md | | `list_recommended_tasks` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-recommended-tasks.md | | `list_reputations` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-reputations.md | | `list_review_queue` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-review-queue.md | | `list_sandbox_executions` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-sandbox-executions.md | | `list_sandbox_templates` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-sandbox-templates.md | | `list_sandboxes` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-sandboxes.md | | `list_security_events` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-security-events.md | | `list_shared_experiences` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-shared-experiences.md | | `list_shared_knowledge` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-shared-knowledge.md | | `list_task_assignments` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-task-assignments.md | | `list_task_events` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-task-events.md | | `list_task_templates` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-task-templates.md | | `list_workflow_runs` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-workflow-runs.md | | `list_workflow_templates` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-workflow-templates.md | | `list_workflow_triggers` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-workflow-triggers.md | | `list_workflow_versions` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-workflow-versions.md | | `list_workflows` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/list-workflows.md | | `orchestrate` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/orchestrate.md | | `orchestrator_daily_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/orchestrator-daily-trend.md | | `recalculate_reputation` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/recalculate-reputation.md | | `recommend_experiences` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/recommend-experiences.md | | `report_progress` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/report-progress.md | | `report_sandbox_violation` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/report-sandbox-violation.md | | `report_step_sandbox_violation` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/report-step-sandbox-violation.md | | `request_approval` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/request-approval.md | | `respond_to_protocol` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/respond-to-protocol.md | | `rollback_workflow` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/rollback-workflow.md | | `scan_conflicts` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/scan-conflicts.md | | `search_knowledge` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/search-knowledge.md | | `search_tasks` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/search-tasks.md | | `security_events_by_agent` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/security-events-by-agent.md | | `security_events_daily_trend` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/security-events-daily-trend.md | | `share_agent_experience` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/share-agent-experience.md | | `suggest_capability_adaptation` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/suggest-capability-adaptation.md | | `timeout_workflow_steps` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/timeout-workflow-steps.md | | `validate_experience` | Read | Low | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/validate-experience.md | | `add_deliberation_message` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/add-deliberation-message.md | | `apply_capability_adaptation` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/apply-capability-adaptation.md | | `apply_experience_decay` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/apply-experience-decay.md | | `auto_resolve_conflicts` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/auto-resolve-conflicts.md | | `broadcast_message` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/broadcast-message.md | | `complete_sandbox_execution` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/complete-sandbox-execution.md | | `complete_workflow_step` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/complete-workflow-step.md | | `create_agent` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-agent.md | | `create_agent_experience` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-agent-experience.md | | `create_channel` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-channel.md | | `create_collaboration_template` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-collaboration-template.md | | `create_knowledge_entry` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-knowledge-entry.md | | `create_protocol` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-protocol.md | | `create_sandbox` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-sandbox.md | | `create_subtask` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-subtask.md | | `create_task` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-task.md | | `create_task_template` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-task-template.md | | `create_workflow` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-workflow.md | | `create_workflow_trigger` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/create-workflow-trigger.md | | `export_security_events` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/export-security-events.md | | `heartbeat_agent` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/heartbeat-agent.md | | `instantiate_sandbox_template` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/instantiate-sandbox-template.md | | `instantiate_task_template` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/instantiate-task-template.md | | `instantiate_workflow_template` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/instantiate-workflow-template.md | | `mark_notifications_read` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/mark-notifications-read.md | | `mark_offline_agents` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/mark-offline-agents.md | | `post_task_event` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/post-task-event.md | | `register_capabilities` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/register-capabilities.md | | `resolve_conflict` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/resolve-conflict.md | | `resolve_protocol` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/resolve-protocol.md | | `resume_workflow_run` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/resume-workflow-run.md | | `self_register_agent` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/self-register-agent.md | | `send_agent_message` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/send-agent-message.md | | `send_channel_message` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/send-channel-message.md | | `set_shared_context` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/set-shared-context.md | | `set_step_runtime_override` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/set-step-runtime-override.md | | `set_task_dod` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/set-task-dod.md | | `submit_task_feedback` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/submit-task-feedback.md | | `update_agent` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-agent.md | | `update_agent_assignment` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-agent-assignment.md | | `update_agent_experience` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-agent-experience.md | | `update_knowledge_entry` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-knowledge-entry.md | | `update_sandbox` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-sandbox.md | | `update_task_assignment` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-task-assignment.md | | `update_task_status` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-task-status.md | | `update_workflow` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-workflow.md | | `update_workflow_trigger` | Write | Medium | https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/update-workflow-trigger.md | ## Tool descriptions - `cancel_workflow_run` — Cancel a running workflow. All pending/running steps are cancelled. - `clear_step_runtime_override` — Clear runtime overrides for a workflow step run, reverting to the workflow definition. - `delete_agent_experience` — Delete (soft-delete) an experience record for an Agent. - `delete_collaboration_template` — Delete a user-created collaboration template. - `delete_knowledge_entry` — Delete (invalidate) a knowledge entry. - `delete_sandbox` — Delete a sandbox policy (only if no active executions reference it). - `delete_shared_context` — Delete a shared context entry by its ID. - `delete_workflow` — Delete a workflow definition. - `delete_workflow_trigger` — Delete a workflow trigger. - `revoke_cross_project_agent` — Revoke an Agent\ - `revoke_sandbox_execution` — Manually revoke (terminate) a running sandboxed execution. - `append_run_logs` — Append log entries to a specific Agent run. Use this during execution to record progress, tool calls, decisions, and errors for later replay and debugging. - `escalate_overdue_tasks` — Trigger priority auto-escalation for overdue tasks. Tasks past their due date that are not yet urgent will have their priority bumped one level (low→medium→high→urgent). Can be called by a cron job or manually. - `handoff_task` — Hand off a task from its current Agent to another Agent. Cancels the active assignment (if any) and creates a fresh assignment + run for the target Agent, recording a handoff event on the timeline. Use this to transfer live work when an … - `launch_workflow` — Launch a new run of a workflow. Creates tasks for each step, assigns matching Agents, and starts entry-point steps (those with no dependencies). - `pause_workflow_run` — Pause a running workflow. Already-running steps continue, but no new steps will be started until resumed. - `retry_workflow_run` — Retry a failed workflow by resetting failed/skipped steps and re-advancing the DAG. - `start_sandbox_execution` — Start a new sandboxed execution for an Agent. Freezes the policy snapshot and returns the execution record + policy envelope. - `acknowledge_conflict` — Mark a conflict as acknowledged (seen). - `authorize_cross_project_agent` — Authorize an Agent to work in a different project. Requires ADMIN/OWNER access to the target project. - `auto_extract_experiences` — Auto-extract experiences from an Agent\ - `auto_extract_knowledge` — Auto-extract knowledge from an Agent\ - `bind_agent_sandbox` — Bind a sandbox policy to an Agent (replaces any existing active binding). - `check_sandbox_action` — Dry-run check whether an action (tool/network/fs_write) is permitted under a sandbox policy. - `claim_agent_task` — Claim a specific task or the next claimable task for an Agent - `claim_cross_project_task` — Claim a task from a cross-project for an Agent. Requires cross-project authorization. - `collaboration_graph` — Platform-wide Agent collaboration graph from direct-message audit logs — nodes (agents with message totals) and undirected edges (message counts between pairs). Useful for visualizing the collaboration network. - `collaboration_metrics` — Retrieve aggregate collaboration metrics for the dashboard: task completion rates, agent utilization, workflow success rates, handoff counts, daily trends, and top agents. - `decay_all_experiences` — System maintenance: apply decay to all agents\ - `diff_workflow_versions` — Compare two versions of a workflow. Returns added, removed, and modified steps. - `discover_agents` — Find available Agents by capability, role, or kind. Useful for discovering which agents can handle a specific type of work. - `discover_cross_project_agents` — Discover agents across all accessible projects, optionally filtered by capability. - `dispatch_tasks` — Coordinator auto-dispatch: have a coordinator Agent distribute claimable (unassigned) tasks across the owner\ - `find_capable_agents_cross_project` — Find agents across all accessible projects that have specific capabilities. - `find_cross_project_tasks` — Find claimable tasks across all projects an Agent is authorized for. - `fire_due_triggers` — Check all active workflow triggers and fire those that are due. Designed to be called periodically by an external scheduler. - `get_agent_capability_gap_analysis` — Agent capability gap analysis. Compares each agent\ - `get_agent_capability_supply_demand` — Analyze supply vs demand for each capability. Supply = agents declaring the capability; demand = active tasks requiring it. Identifies bottleneck (demand exceeds supply), missing (demand, no supply), surplus, and balanced capabilities so… - `get_agent_collaborators` — Aggregate an Agent\ - `get_agent_cross_project_efficiency` — Measure realized value of cross-project Agent authorizations. For each authorization into a project owned by the user, counts completed tasks in the host project within the window. Identifies utilized vs idle (unused) authorizations with… - `get_agent_experience` — Get a specific experience record for an Agent. - `get_agent_experiences_decay_alerts` — Flag Agents whose experience-base confidence is declining. Compares older-half vs newer-half average confidence within the window and returns agents whose confidence dropped beyond a threshold with a recommended action. - `get_agent_failure_error_patterns` — Agent failure error pattern clustering. Groups FAILED AgentRun rows by error text prefix, returning pattern clusters with count, affected agents, peak hour, and hourly distribution. Reveals systemic failure patterns and timing correlations. - `get_agent_failure_reasons` — Distribution of Agent run failure reasons. Buckets FAILED AgentRun rows by a normalized error type (first line of the error text, lowercased, truncated to 80 chars). Returns per-reason counts and affected agent names, sorted by count. Su… - `get_agent_health` — Per-Agent composite health score (0-100) for the current user, combining reputation (0.4), assignment completion rate (0.3), conflict penalty (0.15), and sandbox violation penalty (0.15). Also returns raw sub-scores. Reveals a single com… - `get_agent_health_alerts` — Low-health Agent alert list for the current user. Returns Agents whose composite health_score < min_health_score (default 60), with triggering reasons (low reputation / low completion / conflicts / violations) and concrete improvement re… - `get_agent_health_state_transitions` — Agent health state transition flow. Classifies each agent-day as healthy/degraded/critical based on reputation score thresholds. Counts state-to-state transitions, returning a flow suitable for Sankey visualization. Reveals how often age… - `get_agent_health_trend` — Daily reputation-derived health trend for the current user Agents. Aggregates reputation.update audit entries by day: average new_score (last-seen per agent that day), positive delta count, negative delta count. Also annotates per-day co… - `get_agent_idle_ranking` — Rank Agents by idle duration. Idle time is measured from the most recent of last_seen_at and the latest TaskAssignment activity (completed_at / heartbeat). Classifies each Agent as active (<24h), idle (1-7d), stale (7-30d), dormant (>30d… - `get_agent_inbox` — Retrieve collaboration messages directed at a specific Agent (its @mention inbox) across all of the owner\ - `get_agent_messages` — Get recent direct messages for an Agent (both sent and received). - `get_agent_productivity` — Per-Agent productivity stats for the current user: total assignments, done, failed, cancelled, expired, in-progress, completion rate, and average completion duration (hours) for done assignments. Reveals each Agent throughput and reliabi… - `get_agent_productivity_alerts` — Low-efficiency Agent alert list for the current user. Returns Agents whose completion rate < min_completion_rate (default 50) OR failure rate > max_failure_rate (default 30), with at least min_assignments (default 3) assignments. Each en… - `get_agent_productivity_by_kind` — Productivity comparison grouped by Agent kind for the current user. For each kind (assistant/worker/orchestrator/...), aggregates assignments into totals, done, failed, cancelled, expired, in_progress, agent count, average completion rat… - `get_agent_productivity_calendar_heatmap` — Date × Agent completion calendar heatmap. Buckets done assignments by calendar date (YYYY-MM-DD) and agent_id over the last N days. Returns a {agent_id: {date: count}} matrix, per-agent totals, and date_range. Ideal for GitHub-style cont… - `get_agent_productivity_hourly_heatmap` — Hour-of-day × Agent completion heatmap. Buckets done assignments by the hour (0-23) of completed_at and agent_id, returning a matrix plus per-agent totals and the fleet peak hour. Reveals when each Agent is most productive. - `get_agent_productivity_trend` — Daily Agent assignment completion trend for the current user. Per-day done and failed TaskAssignment counts within the window, plus totals. Reveals whether throughput is rising or falling over time. - `get_agent_productivity_weekly_comparison` — Week-over-week Agent productivity comparison. Returns per-agent done counts for current week vs previous week with change percentage. Reveals which agents are ramping up or slowing down. - `get_agent_reputation` — Get the reputation record for an Agent. Reputation affects task assignment priority. - `get_agent_reputation_history` — Get the timeline of notable reputation changes for an Agent (failures and quality-feedback deltas), reconstructed from audit events. Each point carries the resulting score, so this is useful for charting the reputation trend over time. - `get_agent_run_resource_trend` — Per-agent daily run count and average duration trend. Returns sparkline-friendly daily series for run count and average duration per agent over the lookback window. - `get_agent_run_resource_usage` — Agent run resource usage ranking. Per-agent: total runs, total wall-clock hours, average run duration in minutes. Sorted by total hours descending. Reveals which agents consume the most execution time. - `get_agent_sandbox` — Get the active sandbox bound to an Agent (if any). - `get_agent_skill_matching` — Agent skill matching recommendation. For unassigned in-progress tasks, match task keywords to agent capabilities and experience domains. - `get_agent_specialization_evolution` — Track how each Agent domain coverage evolves over time. Weekly distinct domain count series, revealing specialization vs generalization trends. - `get_agent_task_handoff_stats` — Agent task handoff statistics. Aggregates handoff events by (from_agent, to_agent) pairs, counts frequency and average handoff duration. - `get_agent_workload_forecast` — Forecast each Agent near-future task load via linear regression on daily assignment counts. Returns per-agent slope, multi-day forecast, and recent average. - `get_channel_activity_trend` — Channel activity trend. Per-channel daily message count sparkline and active member count over the lookback window. - `get_collaboration_graph_timeline` — Day-by-day collaboration graph snapshots for timeline replay. Returns bucketed (day/week) snapshots of collaboration edges between agents, showing how collaboration patterns evolve over time. - `get_conflict` — Get a conflict record by ID. - `get_conflicts_by_agent` — Per-Agent conflict involvement counts (total + active), top N by total, enriched with name/kind. Reveals which Agents are most conflict-prone. - `get_conflicts_dashboard` — Aggregate conflict stats for the current user: totals, active count, breakdowns by type/status/severity. - `get_conflicts_sandbox_correlation` — Cross-dimension correlation between Agent conflicts and sandbox violations. For each conflict, checks whether a sandbox violation involving a conflict party occurred within ±window_hours. Reports co-occurrence rate, breakdown by conflict… - `get_conflicts_strategy_stats` — Resolution strategy effectiveness: per-strategy usage count and recurrence rate (fraction of resolved conflicts whose task later saw another conflict). High recurrence flags strategies that suppress rather than solve. - `get_conflicts_trend` — Daily conflict detection vs resolution counts over the last N days (default 30). Each bucket has {date, detected, resolved}. Useful for seeing whether conflicts accumulate faster than they are cleared. - `get_experience_validation_stats` — Get validation statistics for an Agent\ - `get_experiences_confidence_decay_forecast` — Confidence decay forecast using linear regression on daily averages. Projects 7 days ahead, reports regression slope, R-squared, and estimated days until average confidence drops below 0.5. Reveals whether the experience pool is decaying… - `get_experiences_confidence_distribution` — Confidence interval distribution for the user valid experiences. Buckets into 5 intervals (0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8, 0.8-1.0) with count, percentage, and average reuses. Reveals whether the experience pool is mostly high- or low-… - `get_experiences_decay_by_domain` — Per-domain decay comparison for the user valid experiences. Aggregates by domain: total, active (confidence>=0.5), decayed (confidence<0.5), average confidence, total reuses. Sorted by decayed count descending. Reveals which knowledge do… - `get_experiences_decay_by_task_type` — Per-task-type decay comparison for the user valid experiences. Same as decay-by-domain but grouped by task_type. Reveals which task categories have the most stale / low-confidence entries. - `get_experiences_low_confidence` — List the current user valid experiences with confidence below max_confidence (default 0.5), sorted by confidence ascending. Each entry includes agent_id, domain, task_type, experience_type, confidence, times_reused, key_learnings excerpt… - `get_experiences_propagation_chain` — Experience sharing propagation chain. Groups shared experiences by source agent with shared_count, total_reuses, top domains, and top propagated experiences. Reveals which agents contribute most to collective learning and how knowledge f… - `get_experiences_reuse_trend` — Daily reuse + decay trend for the user valid experiences. Buckets experiences by last-reused (or creation) date. Per day: experiences reused, total reuse count, average confidence, decayed count (confidence<0.5). Reveals whether reuse ke… - `get_experiences_scatter` — Confidence × reuse-count scatter points for the user valid experiences. One point per experience: confidence, times_reused, domain, task_type, experience_type. Reveals whether high-confidence experiences actually get reused more. Caps vi… - `get_experiences_skill_coverage_radar` — Per-Agent skill coverage radar across experience domains. Returns top N domains and per-agent normalized scores (0-100) for radar/spider chart rendering. Reveals skill gaps and specialization patterns across the agent fleet. - `get_experiences_source_distribution` — Experience count by creation source. Groups by origin: manual (no workflow run), workflow (has source_workflow_run_id), auto_step (has source_step_key but no workflow). Per-source: count, percentage, avg confidence, avg reuses. Reveals w… - `get_experiences_stats` — Aggregate AgentExperience stats for the current user: totals, breakdowns by domain/task_type/experience_type, shared count, total reuses, average confidence. Reveals where the collective knowledge base is concentrated. - `get_knowledge_entry` — Get a specific knowledge entry by ID. - `get_knowledge_propagation_network` — Cross-Agent knowledge propagation network. Nodes are Agents sharing experiences, edges connect contributors weighted by reuse count. Reveals which Agents propagate knowledge most broadly. - `get_orchestrator_status` — Return the state of the built-in orchestrator scheduler (enabled/disabled) and the last orchestration cycle summary, if the scheduler is enabled via ORCHESTRATOR_ENABLED. - `get_project_info` — Get detailed project information including statistics and configuration. Provide either project_id or project_name. - `get_project_tasks_by_name` — Get all pending tasks for a project by project name, sorted by creation time - `get_protocol` — Get a protocol with all its messages/responses. - `get_protocol_analytics` — Get analytics for collaboration protocols: usage by type, resolution rates, participation. - `get_protocol_decision_latency` — Collaboration protocol decision latency analysis. For resolved protocols, computes creation-to-resolution latency aggregated by protocol type (avg/median/min/max). - `get_run_logs` — Retrieve append-only log entries for a specific Agent run. Agents write logs during execution to record progress, tool calls, decisions, and errors. Supports incremental polling with since_id. - `get_sandbox` — Get a sandbox policy by ID. - `get_sandbox_dashboard` — Get aggregate sandbox stats for the current user: total sandboxes, executions, violations, breakdowns. - `get_sandbox_execution` — Get a sandbox execution record with its violations. - `get_sandbox_template_usage` — Sandbox policy template instantiation stats: per-template usage count and how many instances were bound to an Agent. Reveals which preset templates are most popular. - `get_sandbox_violation_trend` — Daily sandbox violation counts + by-type breakdown over the last N days (default 30). Useful for spotting whether a policy change or Agent change is producing more violations. - `get_sandbox_violations_by_agent` — Per-Agent sandbox violation counts over the last N days, top N by total, enriched with name/kind and a by-violation-type sub-count. Reveals which Agents most frequently attempt disallowed actions. - `get_shared_context` — Read shared context entries for a task. Agents use the shared context to persist intermediate results, references, scratch notes, or structured data that other Agents need. If key is provided, only the matching entry is returned; otherwi… - `get_step_effective_params` — Get the effective parameters for a workflow step run (runtime overrides merged with the step definition). - `get_step_sandbox_execution` — Get the sandboxed execution (if any) bound to a workflow step run. Surfaces the auto-started execution + frozen policy snapshot + violations. - `get_task_allocation_fairness` — Task allocation fairness analysis. Computes Gini coefficient and Lorenz curve for task distribution across agents. Identifies allocation inequality: Gini 0 = equal, 1 = all tasks to one agent. - `get_task_by_id` — Get detailed task information by task ID - `get_task_comment_sentiment_trend` — Task comment sentiment trend. Aggregates comment events by day and classifies sentiment (positive/negative/neutral) based on keyword matching. - `get_task_completion_by_assignee` — Daily task completion trend grouped by assignee (Agent). Buckets done assignments by calendar day of completed_at and agent_id, returning per-agent daily series plus totals (top N by total completed). Reveals which agents are actively de… - `get_task_completion_by_priority` — Task completion rate by priority. Groups tasks by priority with total/done/cancelled/completion_rate. Reveals whether high-priority tasks are delivered at a comparable rate to low-priority ones. - `get_task_completion_by_project` — Daily task completion trend grouped by project. Buckets done tasks by calendar day of completed_at and project_id, returning per-project daily series plus totals (top N by total completed). Reveals which projects are actively delivering … - `get_task_completion_forecast` — Task completion forecast based on historical velocity. Computes daily done-task velocity over the lookback window, extrapolates to estimate when remaining tasks will be completed, with per-priority breakdown. - `get_task_completion_rate_by_project` — Task completion rate snapshot comparison across projects. Groups tasks by project with total/done/in_progress/cancelled/completion_rate. Reveals which projects have the best/worst delivery rates. - `get_task_dependency_chain` — Task dependency chain analysis. Finds root tasks with subtask hierarchies, computes chain depth, total tasks, completion progress. - `get_task_evidence` — Get a task - `get_task_overdue_by_assignee` — Overdue task count grouped by assignee (Agent). Per agent: overdue count, by-priority breakdown, earliest overdue due_date. Sorted by overdue count descending. Reveals which agents bear the heaviest overdue burden. - `get_task_overdue_clustering` — Overdue task clustering analysis by project and priority. Per cluster: project name, priority, count, avg days overdue, representative task titles. Reveals where overdue tasks concentrate and why. - `get_task_overdue_trend` — Daily overdue task trend by due_date: per-day overdue count (due_date7d), average completion … - `get_workflow` — Get a single workflow definition with its steps. - `get_workflow_failed_steps_by_duration` — Rank failed workflow steps by average wall-clock duration (finished - started). Per step_key: failures count, avg/median/max duration in seconds, sorted by avg duration descending. Reveals which failing steps burn the most time before gi… - `get_workflow_failure_correlation` — Cross-dimension correlation between failed workflow steps and collaboration conflicts / sandbox violations. For each failed step, checks whether a conflict or sandbox violation involving the same Agent occurred within ±window_hours. Repo… - `get_workflow_failure_correlation_by_step` — Per-step-key failure correlation with conflicts / sandbox violations. Aggregates the same ±window_hours co-occurrence by step_key, returning for each step: failed count, with_conflict, with_violation, and rates. Reveals which steps most … - `get_workflow_run` — Get a single workflow run with step details. - `get_workflow_run_console` — Step-level real-time console for a workflow run. Aggregates each step run with its sandbox execution, effective params (runtime overrides merged with definition), recent run logs, duration, and any conflicts tied to the run — a single pa… - `get_workflow_run_duration_percentiles` — Daily trend of workflow run duration percentiles (P50/P90/P95). For each day, aggregates completed WorkflowRun durations and returns percentiles. Useful for spotting regressions in workflow execution time. - `get_workflow_run_trend` — Daily workflow run outcome trend: per-day succeeded vs failed counts over the last N days (default 30), using finished_at. Useful for charting workflow reliability over time. - `get_workflow_similarity_matrix` — Workflow run similarity matrix. Computes pairwise Jaccard similarity between workflow run step_key sets. Returns matrix and most/least similar run pairs. Reveals how consistent workflow executions are. - `get_workflow_step_bottleneck_timeline` — Per-step daily average duration timeline. Tracks how each workflow step avg duration changes over time to spot regressions or improvements. - `get_workflow_step_cofailure_matrix` — Step-key co-failure matrix. For each failed workflow run, collects failed step_keys. Builds a symmetric co-occurrence matrix showing which steps tend to fail together, indicating shared failure causes or cascading failures. - `get_workflow_step_dependency_bottleneck` — Workflow step dependency bottleneck analysis. Computes DAG critical path (longest duration path) per workflow, identifies bottleneck steps by their share of total critical path time. Reveals which steps dominate workflow execution time. - `get_workflow_step_duration_histogram` — Workflow step duration histogram. Buckets completed step durations into time ranges (0-10s, 10-30s, 30-60s, 60-120s, 120-300s, 300s+) per step_key. - `get_workflow_step_failure_rate` — Per-step-key failure rate ranking. For each step_key: total runs, failed count, failure rate percentage. Sorted by failure rate descending. Reveals which workflow steps are the least reliable. - `get_workflow_step_hourly_distribution` — Step execution hour-of-day distribution. Groups WorkflowStepRun by (step_key, hour) based on started_at. Returns per-step hourly distribution and business-hours ratio. Reveals which steps run during business hours vs overnight. - `get_workflow_step_retry_topology` — Step retry topology. Groups WorkflowStepRun by step_key, counting retries (attempt>1), first-attempt success rate, and retry success rate. Reveals whether retries actually recover failures and which steps are most retried. - `get_workflow_step_stats` — Per-step-key execution stats across the user workflow runs: total/succeeded/failed/skipped, success rate, and average duration. Reveals bottleneck and chronic-failure steps. - `get_workflow_structural_complexity` — Analyze design-time structural complexity of active workflows. For each workflow computes DAG metrics from step dependencies: step count, max dependency depth (longest chain), total edges, average fan-in/fan-out, and root/leaf step count… - `get_workflow_success_rate_by_workflow` — Per-workflow run success rate comparison over the last N days (default 30). Returns top workflows by total finished runs with succeeded/failed/cancelled counts, success_rate, and avg_duration. Reveals which workflows are most/least relia… - `get_workflow_template` — Get details of a specific workflow template by key. - `get_workflow_version` — Get a specific version snapshot of a workflow. - `health_check` — Run a full platform health check: expire stale agents, expire stale leases, and escalate overdue tasks. Designed to be called periodically by a cron job. Returns a summary of actions taken. - `ignore_conflict` — Dismiss a conflict without action. - `instantiate_collaboration_template` — Instantiate a collaboration template: creates the Agents, a collaboration channel, and optionally launches the attached workflow. - `learn_from_experience` — An Agent internalizes a shared experience from another Agent for collective learning. - `list_agent_assignments` — List task assignments for an Agent - `list_agent_cross_projects` — List all projects an Agent is authorized to work in. - `list_agent_experiences` — List experiences for an Agent. Experiences capture success/failure patterns from past tasks. - `list_agents` — List Agent identities available to the current user - `list_audit_logs` — Query the immutable audit trail for platform operations. Supports filtering by action type, resource type, actor, and project. - `list_channel_messages` — List messages in a collaboration channel, in chronological order. - `list_channels` — List collaboration channels. Multiple Agents can join a channel to discuss and coordinate on tasks. - `list_collaboration_templates` — List collaboration templates (built-in and user-created). Each template defines a team of Agents that work together. - `list_conflicts` — List collaboration conflicts for the current user, optionally filtered by status/type. - `list_knowledge_entries` — List knowledge entries for an Agent. Agents store insights, patterns, and solutions for cross-task reuse. - `list_my_tasks` — List tasks relevant to you (created by, owned by, in your projects, or assigned to you). Entry point to discover work - `list_notifications` — List persistent notifications for the current user. Notifications are created when collaboration events (claim, dispatch, handoff, message, question, etc.) happen on tasks the user owns. Use this to catch up on missed events when coming … - `list_orchestrator_history` — Return recent orchestration run records for trend analysis — per-run stats (stale agents, timed-out steps, triggers fired, conflicts auto-resolved, duration, errors, triggered_by manual|scheduler) plus trend aggregates. - `list_project_external_agents` — List all external Agents authorized to work in a project. - `list_protocols` — List collaboration protocols (proposals, votes, consensus, auctions, handoffs) with optional filters. - `list_recommended_tasks` — List unassigned tasks that match an Agent\ - `list_reputations` — List reputation records for all your Agents, ranked by score. - `list_review_queue` — List Agent assignments that need human feedback or final review - `list_sandbox_executions` — List executions under a sandbox policy. - `list_sandbox_templates` — List preset sandbox policy templates (read_only_research, code_generation, data_analysis, full_autonomy, sandboxed_review). - `list_sandboxes` — List Agent sandbox policies owned by the current user. Optionally filter by agent_id or active_only. - `list_security_events` — Unified security event feed: aggregates sandbox violations, agent conflicts, and security-relevant audit entries (sandbox./conflict./reputation./workflow_step_overridden) into a single time-ordered list. Each event is normalized to {even… - `list_shared_experiences` — List shared experiences from other Agents that this Agent can learn from. - `list_shared_knowledge` — List knowledge entries shared with projects the current user is a member of. - `list_task_assignments` — List Agent assignments for a task, including active leases and assigned Agents - `list_task_events` — List collaboration events for a task so Agents can inspect handoffs, claims, review requests, and lease expirations - `list_task_templates` — List reusable task templates owned by the current user. Templates define default title, content, priority, tags, and capabilities for quickly creating new tasks. - `list_workflow_runs` — List workflow runs for the current user. - `list_workflow_templates` — List built-in workflow templates for common multi-Agent collaboration patterns (e.g. code review pipeline, research & report, bug fix flow). - `list_workflow_triggers` — List scheduled workflow triggers owned by the current user. - `list_workflow_versions` — List version history for a workflow. Each update creates a snapshot. - `list_workflows` — List workflow definitions. A workflow is a DAG of steps that coordinate multiple Agents in sequence or parallel (e.g. - `orchestrate` — Global collaboration orchestrator: runs the full multi-Agent maintenance cycle in one call — (1) health (stale agents, expired leases, overdue escalation), (2) workflow step timeouts + re-advance, (3) fire due workflow triggers, (4) conf… - `orchestrator_daily_trend` — Daily aggregation of orchestration runs, aligned with the security events daily-trend time dimension so the two can be rendered on a unified timeline. Each day includes runs, manual/scheduler split, triggers fired, conflicts resolved, er… - `recalculate_reputation` — Recalculate an Agent\ - `recommend_experiences` — Recommend relevant experiences for an Agent given a task context. Searches own and shared experiences. - `report_progress` — Append a progress log entry to a task (append-only task log) to keep humans informed while working - `report_sandbox_violation` — Report a policy violation during a sandboxed execution. Optionally terminate the execution. - `report_step_sandbox_violation` — Report a sandbox policy violation for a workflow step execution. If terminate_step is true, the step is marked FAILED and the sandboxed execution is marked VIOLATED. - `request_approval` — Ask the human to decide something about a task (destructive operation, budget, scope change). The request enters the workspace approval queue for owner/admin to approve or reject - `respond_to_protocol` — Respond to a protocol (vote, bid, accept, reject, counter-proposal, comment). Some responses auto-resolve the protocol. - `rollback_workflow` — Rollback a workflow to a specific version. Creates a snapshot of the current version first. - `scan_conflicts` — Run a conflict detection scan: duplicate claims, stale assignments, protocol deadlocks. Creates conflict records for new issues. - `search_knowledge` — Search an Agent\ - `search_tasks` — Search accessible tasks by keyword in title or content - `security_events_by_agent` — Per-agent aggregation of security events for ranking. Reuses the same filters as list_security_events. Returns agents: [{agent_id, name, total, sandbox_violation, conflict, audit, CRITICAL, WARNING, INFO}] sorted by total desc (top 50). … - `security_events_daily_trend` — Daily aggregation of security events for trend visualization. Reuses the same filters as list_security_events (agent_id, workflow_run_id, event_type, severity, since, until, search). Returns days: [{date, sandbox_violation, conflict, aud… - `share_agent_experience` — Share an Agent\ - `suggest_capability_adaptation` — Suggest capability adaptations for an Agent based on its experience patterns. Returns suggested additions/removals. - `timeout_workflow_steps` — Scan all running workflow steps and mark those that have exceeded their timeout_seconds as FAILED, then advance the affected workflows. Designed to be called periodically. - `validate_experience` — Cross-validate an experience by another Agent. Confirm or refute accuracy to adjust confidence. - `add_deliberation_message` — Add a deliberation message (argument/evidence/comment) to a deliberation protocol. Enables multi-round discussion before voting. - `apply_capability_adaptation` — Apply capability adaptations to an Agent (add or remove capabilities). - `apply_experience_decay` — Apply time-based confidence decay to an Agent\ - `auto_resolve_conflicts` — Maintenance: scan for conflicts and auto-resolve low-severity ones (INFO/WARNING) using their suggested strategy if it is safe (auto_retry/least_loaded). CRITICAL conflicts are never auto-resolved. - `broadcast_message` — Send a broadcast message from one Agent to all other active Agents owned by the same user. Useful for coordination signals like - `complete_sandbox_execution` — Mark a sandboxed execution as completed with aggregated usage stats. - `complete_workflow_step` — Mark a workflow step as completed (or failed) and advance the DAG. This is the callback that Agents call when they finish a step. The result_summary is automatically saved to SharedContext for downstream steps. - `create_agent` — Create an Agent identity and declare its collaboration capabilities - `create_agent_experience` — Manually create an experience record for an Agent. - `create_channel` — Create a collaboration channel for multi-Agent discussion. Agents can be auto-added as members. - `create_collaboration_template` — Create a custom collaboration template defining a team of Agents. - `create_knowledge_entry` — Create a knowledge entry for an Agent. Store insights, patterns, or solutions for future reuse. - `create_protocol` — Create a collaboration protocol (proposal, vote, consensus, auction, or handoff) for structured multi-Agent decision making. - `create_sandbox` — Create a new Agent sandbox policy governing tool/network/filesystem/resource access during execution. - `create_subtask` — Create a child task under a parent task so an Agent can decompose work. The child inherits the parent\ - `create_task` — Create a new task in the specified project - `create_task_template` — Create a reusable task template. Templates let you quickly create new tasks with predefined title, content, priority, tags, and required capabilities. - `create_workflow` — Create a new workflow definition with steps. Each step specifies required Agent capabilities, optional task template, and dependency edges (depends_on). The system picks a matching Agent at runtime. - `create_workflow_trigger` — Create a scheduled trigger for a workflow. Supports cron expressions for recurring runs and one-shot schedules. - `export_security_events` — Export the unified security event feed as CSV or JSON text (up to 1000 rows). Accepts the same filters as list_security_events (agent_id, workflow_run_id, event_type, severity, since, until, search) plus format (csv | json, default csv).… - `heartbeat_agent` — Record a heartbeat for an Agent and optionally update its availability status - `instantiate_sandbox_template` — Create a sandbox policy from a preset template, optionally overriding fields and binding to an agent. - `instantiate_task_template` — Create a new task from a template. The task inherits the template\ - `instantiate_workflow_template` — Create a workflow from a built-in template. Optionally override name and project context. - `mark_notifications_read` — Mark one or more notifications as read. Pass all=true to mark everything read, or pass an array of IDs to mark specific items. - `mark_offline_agents` — Scan all active/paused agents and mark those whose last heartbeat exceeds the offline threshold (30 min) as OFFLINE. Cancels their running assignments. Designed to be called periodically. - `post_task_event` — Post a collaboration message to a task timeline so Agents can communicate: leave notes, ask/answer questions, hand off work to another Agent, raise blockers, or record decisions. Provide agent_id to post as that Agent, omit it to post as… - `register_capabilities` — Register new capabilities for an Agent at runtime. Use mode - `resolve_conflict` — Resolve a conflict with a chosen strategy. For duplicate claims, FIRST_WINS/HIGHEST_REPUTATION/LEAST_LOADED also revokes losing assignments; for stale assignments, AUTO_RETRY expires them. - `resolve_protocol` — Manually resolve a protocol (force accept/reject/cancel). - `resume_workflow_run` — Resume a paused workflow. The DAG engine re-evaluates which steps can start. - `self_register_agent` — Self-register an Agent into the platform. If an agent with the same name+provider already exists, it updates the record (idempotent). Use this when an external Agent starts up and wants to announce itself. - `send_agent_message` — Send a direct message from one Agent to another. Delivered via SSE (real-time) and Notification (persistent). Optionally attached to a task. - `send_channel_message` — Send a message to a collaboration channel. All channel members will receive the message. - `set_shared_context` — Create or update a shared context entry for a task (upsert by task_id + key). Use this to store intermediate results, plans, references, or notes that other Agents on the same task can read later. - `set_step_runtime_override` — Dynamically reconfigure a not-yet-terminal workflow step (runtime overrides). Only PENDING/WAITING steps accept start-time params; RUNNING steps accept only timeout_seconds/retry_count. - `set_task_dod` — Set a task - `submit_task_feedback` — Submit feedback for a completed or in-progress task - `update_agent` — Update an Agent identity, status, model metadata, or capabilities - `update_agent_assignment` — Update an Agent assignment state, progress, feedback, or execution result - `update_agent_experience` — Update an experience record for an Agent. - `update_knowledge_entry` — Update a knowledge entry (title, content, tags, confidence, etc.). - `update_sandbox` — Update an existing sandbox policy. - `update_task_assignment` — Update a task assignment as the current user or coordinator. Use this to approve, resume, or cancel items from list_review_queue. - `update_task_status` — Update a task - `update_workflow` — Update a workflow definition and its steps (full replacement of steps if provided). - `update_workflow_trigger` — Update a workflow trigger. Only provided fields are changed. ## Related servers - UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md - Delx Protocol — Agent Recovery & Continuity (1076 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-protocol.md - Delx Mcp A2a (1068 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md - Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md - MCP Framework Personal (811 tools) — https://policylayer.com/tools/inggerman-mcps.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 - Eda Agent (726 tools) — https://policylayer.com/tools/eda-agent.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=todo-for-ai-todo-for-ai-mcp · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/todo-for-ai-todo-for-ai-mcp