New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice
// SCAN REPORT

Todos

528 tools. 264 can modify or destroy data without limits.

37 destructive tools with no built-in limits. Policy required.

Last updated:

264 can modify or destroy data
264 read-only
528 tools total

Community server · catalogue entry checked 15/08/2026

How to control Todos ↓

TOOL MAP

What Todos exposes to your agents

Read (264) Write / Execute (227) Destructive / Financial (37)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Todos tools

Destructive · High bulk_delete_tasks This tool irreversibly removes task records from the system. Destructive · High cancel_agent_run Cancelling a running or queued agent run is an irreversible action — the run is terminated and cannot be resumed. Destructive · Medium cancel_agent_run_dispatch Cancelling a running or queued dispatch is an irreversible action — the dispatched agent run is terminated and cannot be simply un-cancelled. Destructive · Medium cancel_dispatch Cancelling a dispatch is an irreversible action — once cancelled, the scheduled dispatch is removed and cannot be restored.

264 of Todos's 528 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Todos

PolicyLayer is an MCP gateway — it sits between your AI agents and Todos, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "apply_retention_cleanup": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "acknowledge_handoff": {
    "limits": [
      {
        "counter": "acknowledge_handoff_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_branch_work": {
    "limits": [
      {
        "counter": "analyze_branch_work_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Todos — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON TODOS →

Instant setup, no code required.

FULL CATALOGUE

All 528 Todos tools

DESTRUCTIVE 37 tools
Destructive apply_retention_cleanup Apply local retention cleanup after a dry run. Requires confirm= Destructive bulk_delete_tasks Delete multiple tasks at once. Tasks with active children are skipped. Destructive cancel_agent_run Cancel a queued or running agent run. Destructive cancel_agent_run_dispatch Cancel a queued or running local agent dispatch. Destructive cancel_dispatch Cancel a pending or scheduled dispatch. Cannot cancel dispatches that have already been sent. Destructive cleanup_artifacts Purge soft-deleted artifacts past retention period from local store. Destructive delete_agent Archive an agent (soft delete). The agent is hidden from list_agents but preserved for task history. Use unarc Destructive delete_artifact Soft-delete a local artifact. Use cleanup_artifacts to purge expired deletions. Destructive delete_comment Delete a comment. Destructive delete_label Permanently delete a label. Destructive delete_milestone Delete a local roadmap milestone. Destructive delete_plan Permanently delete a plan and all its tasks. Destructive delete_project Permanently delete a project and all its tasks. Destructive delete_roadmap Delete a local roadmap and its milestone/release config. Destructive delete_search_view Delete a local saved search view. Destructive delete_tag Permanently delete a tag. Removes it from all tasks. Destructive delete_task Permanently delete a task. Fails if the task has active children (tasks that depend on it). Destructive delete_task_list Permanently delete a task list and all its tasks. Destructive delete_template Delete a task template by ID. Destructive delete_watch_rule Delete a local terminal watch rule by ID. Destructive machines_archive Archive (soft-delete) a machine. Cannot archive primary or machines with active tasks. Destructive machines_delete Hard-delete a machine. Cannot delete primary or machines with active tasks. Destructive remove_agent_run_adapter Remove a configured local agent run adapter. Destructive remove_capacity_profile Remove a local planning capacity profile. Destructive remove_encryption_profile Remove a local encryption profile. Destructive remove_local_event_hook Remove a configured local event hook. Destructive remove_local_extension Remove a local workflow extension from the registry. Destructive remove_policy_pack Remove a local policy pack. Destructive remove_review_routing_rule Remove a local review routing rule. Destructive remove_runner_sandbox_profile Remove a local runner sandbox profile. Destructive remove_task_dependency Remove a dependency between two tasks. Destructive remove_task_relationship Remove a semantic relationship between tasks by ID or by source+target+type. Destructive remove_terminal_notification_rule Remove a configured local terminal notification watch rule. Destructive remove_verification_provider Remove a configured local verification provider. Destructive remove_workspace_trust Remove a local workspace trust profile. Destructive restore_database Restore todos SQLite database from a local backup file. Destructive unfocus Clear focus — show all projects and tasks.
EXECUTE 30 tools
Execute begin_task_run_transaction Preview or apply an idempotent local loop run transaction keyed by a stable loop/run id. Execute build_context_pack Generate local agent context pack (JSON + Markdown prompt bundle) for a task, project, or plan. Execute check_database_integrity Run PRAGMA quick_check and foreign key validation on local SQLite DB. Execute claim_next_agent_run Atomically claim the next queued local agent run. Execute dispatch_task_list Legacy/emergency only: send all tasks from a task list to a tmux window after a human explicitly chooses tmux Execute dispatch_tasks Legacy/emergency only: send specific tasks to a tmux window after a human explicitly chooses tmux delivery. No Execute dispatch_to_multiple Legacy/emergency fan-out: send the same tasks or task list to multiple tmux windows in sequence after a human Execute enqueue_agent_run Queue a local agent run for a task or plan. Execute evaluate_terminal_watch_rules Evaluate all local terminal notification watch rules against a sample event. Execute install_local_extension Install or update a local workflow extension from a manifest, directory, or offline bundle. Execute preview_user_scaffold Dry-run preview of a user scaffold with variables. Execute process_reminders Fire due local reminders; optional desktop notify-send when enabled. Execute queue_agent_run Queue a local agent run for a task and attach a run ledger ID. Does not call hosted runners. Execute require_approval_gate Create a local manual approval checkpoint before risky task or run work. Execute retry_agent_run Manually re-queue a failed or cancelled agent run. Execute retry_agent_run_dispatch Queue a retry for a previous local agent dispatch. Execute run_agent_workflow_demo Run a scripted local agent workflow demo (agents, projects, tasks, runs) using an ephemeral database. Execute run_doctor Run local doctor diagnostics and optionally apply safe repairs after dry-run review. Execute run_due_dispatches Legacy/emergency only: manually trigger all pending tmux dispatches that are due (scheduled_at <= now). Return Execute run_next_agent_dispatch Run the next queued local agent dispatch, optionally as a dry-run. Execute run_release_checks Run public package release and supply-chain hardening checks. Execute run_saved_view Execute a saved view by slug or id. Execute run_verification Run a local verification provider and store normalized evidence record. Execute run_verification_provider Run a local verification provider and optionally record task verification evidence. Execute simulate_agent_replay Dry-run replay a recorded local agent context pack or run fixture without mutating the task database. Execute start_focus_session Start a local focus session for a task, plan, run, or general agent work. Execute test_local_event_hook Deliver a test event to one configured local event hook. Execute test_local_extension_compatibility Run local CLI/MCP compatibility checks and runner sandbox dry-runs for an extension without installing it. Execute test_terminal_notification_rule Evaluate one local terminal notification watch rule against a sample event. Execute watch_source_todos Run finite local source TODO watcher scans. Uses polling, respects .gitignore/excludes, and can dry-run or app
WRITE 197 tools
Write acknowledge_handoff Mark a local handoff as read for one agent. Write acquire_task_lease Atomically acquire a task lease with TTL for multi-agent coordination. Write add_artifact Attach a local file as an artifact for a task, project, plan, run, verification, or handoff. Files stay local- Write add_comment Alias for create_comment. Write add_task_dependency Add a dependency (this task won Write add_task_file Link a file path to a task. Tracks which files an agent is working on. Upserts if same task+path exists. Auto- Write add_task_relationship Create a semantic relationship between two tasks (related_to, conflicts_with, similar_to, duplicates, supersed Write add_task_run_artifact Record a local artifact for a run in the content-addressed store, or metadata only when content is unavailable Write add_task_run_command Record local command/test evidence for a run and mirror it into task verification evidence. Write add_task_run_event Record a local run event such as progress, comment, claim, command, file, artifact, completed, failed, or canc Write add_task_run_file Record a file touched by a local run and link it to the task. Write add_task_verification Record a local verification command, status, summary, and optional artifact path for a task. Write append_run_command Append a command entry and optional stdout/stderr to a run record (redacted). Write apply_export_profile Apply secure export profile (redacted, encrypted, plaintext with explicit acknowledgement) to data bundle. Write apply_failure_triage Apply triage action: annotate, retry, reopen, split, or escalate on a failed task/run. Write apply_user_scaffold Apply a user scaffold (materialize tasks/plans where supported). Write approve_approval_gate Approve a local manual approval checkpoint. Write approve_gate Approve a pending approval gate request. Write approve_review_item Approve a local review queue item. Write approve_task Approve a task that requires_approval. Records who approved it. Write archive_completed Auto-archive completed tasks older than the threshold (default 7 days). Returns count. Write assign_label_to_task Assign a label to a task (syncs to tags for search compatibility). Write attach_plan_to_project Attach a plan to a project and initialize plan execution mode. Write auto_assign_task Automatically assign a task to the best-fit agent based on capabilities, current load, and focus mode. Write backup_database Create a local atomic backup of the todos SQLite database. Write bootstrap_workspace Bootstrap local todos project: register identity, default task list, todos.md, manifest. Write bulk_create_tasks Create multiple tasks at once from an array of task objects. Write bulk_update_tasks Update multiple tasks at once. All tasks must pass the dependency check. Write cancel_task Mark a task as cancelled. Write capture_knowledge_snapshot Capture a project knowledge snapshot bundling decisions, plans, and conventions. Write claim_goal_step Claim the next ready /goal step for an agent (equivalent to /goal execute). Write claim_next_task Atomically claim and start the best available pending task for an agent. Write claim_plan_step Claim and start the next ready plan step for an agent. Write claim_review_item Claim a task from the local review queue. Write claim_task Alias for start_task — mark a task as in_progress and assign it to the calling agent. Write close_risk Close a local risk as resolved or accepted. Write complete_agent_run Mark a running agent run as completed with optional evidence. Write complete_task Mark a task completed. Optionally set confidence, score, and completion timestamp. Write create_board Create a local task or plan kanban board with configurable workflow lanes and WIP limits. Write create_branch_work_plan Create a local branch-safe work plan from task or plan files, local file conflicts, and git status. Write create_calendar_item Create a local calendar reminder, milestone, or work block. Write create_comment Add a comment to a task. Write create_custom_field Define a user custom field for tasks. Write create_decision_record Create an ADR-style local decision record. Write create_goal_workflow Create a /goal-style plan with decomposed step tasks (local-only). Write create_handoff Create a session handoff note for agent coordination. Write create_handoff_packet Build and persist a handoff packet locally. Write create_inbox_intake Create a task from local inbox intake with dedupe, redaction, and source metadata. Write create_inbox_item Capture a local inbox item from pasted errors, CI logs, git context, files, or GitHub issue URLs. Creates a li Write create_knowledge_record Create a local project knowledge record for decisions, architecture notes, tradeoffs, or task-linked context. Write create_knowledge_snapshot Save a local context snapshot and attach it as a project knowledge record. Write create_label Create a new label. Write create_local_backup Create a local backup bundle with manifest checksums for tasks, projects, plans, runs, comments, evidence, and Write create_manual_checkpoint Create a manual checkpoint on a task, optionally requiring approval. Write create_milestone Add a local milestone to a roadmap. Write create_nl_intake Create a task from natural-language intake with local parsing, dedupe, and redaction. Write create_plan Create a new plan (sprint/milestone). Write create_project Create a new project. Write create_reminder Create a custom local reminder. Write create_retrospective Create a local retrospective report for a project or plan from completed plans, missed estimates, recurring bl Write create_risk Create a local project or plan risk register entry. Uses only local SQLite state. Write create_roadmap Create a local roadmap for grouping milestones, plans, tasks, runs, and release labels. Write create_run_record Create a first-class local run record for agent execution logging. Write create_saved_view Create a saved search filter/view. Write create_tag Create a new tag. Write create_task Create a new task in a project. Pass short_id=null to auto-generate. Write create_task_from_template Create task(s) from a template. For multi-task templates, creates all tasks with dependencies wired. Supports Write create_task_list Create a new task list. Write create_template Create a reusable task template. Optionally include a tasks array to define a multi-task template with depende Write create_verification_evidence Create a portable verification evidence record with commands, test results, CI links, and artifact refs. Write create_watch_rule Create a local terminal watch rule. Write detect_file_relationships Auto-detect tasks that modify the same files and create modifies_same_file relationships. Write dismiss_reminder Dismiss a local reminder by ID. Write encrypt_metadata_fields Encrypt sensitive fields in a metadata object using local key (TODOS_ENCRYPTION_KEY or key file). Write export_report_file Write a read-only HTML or Markdown report file to a local path. Write export_todos_md Export tasks to a local todos.md markdown file. Write extend_task Add more time to a task Write extract_todos Scan source files for TODO/FIXME/HACK/BUG/XXX/NOTE comments and create tasks from them. Deduplicates on re-run Write fail_agent_run Mark an agent run as failed (auto-retries if configured). Write fail_task Mark a task as failed. Increments retry_count. Sets back_on_board=false so agent stays assigned. Write finish_task_run Finish a local run ledger entry as completed, failed, or cancelled. Supports idempotent lookup by key. Write generate_branch_work_plan Generate a safe step-by-step branch integration work plan for agents. Write generate_release_notes Generate local release notes from git commits and completed tasks. Write heartbeat Update your last_seen_at timestamp to signal you Write import_calendar_ics Import VEVENT entries from ICS text as local calendar items. Write import_external_issues Dry-run or apply local imports from GitHub, Linear, Jira, or plain URL issue data with source-metadata dedupe. Write import_handoff Preview or apply a deterministic local handoff bundle. Write import_issues Import GitHub, Linear, or Jira issues from local JSON export files with dedupe. Write import_local_bundle Import a local JSON bundle with merge strategy and conflict metadata. No cloud calls. Write import_onboarding_fixture Dry-run or apply a bundled local onboarding fixture import. Dry-run is the default. Write import_roadmap Preview or apply a local roadmap JSON bundle. Write import_template Import a template from a JSON string (as returned by export_template). Creates new template with new IDs. Write import_todos_md Import tasks from a local todos.md markdown file. Write init_templates Initialize the bundled local template library. Skips templates that already exist by name. Write install_template_library Install all bundled templates into local database (idempotent). Write link_task_git_ref Link a local git branch or pull request to a task. Upserts on task, ref_type, and name. Write link_task_git_trace Link a task to local git context: commit, branch, changed files, optional PR and CI snapshot. Write link_task_to_commit Link a git commit SHA to a task. Creates an audit trail: task → commits. Upserts on same task+sha. Write lock_file Acquire an exclusive lock on a file path. Throws if another agent holds an active lock. Same agent re-locks re Write lock_task Acquire or renew a local task lock lease for an agent. Write log_time Log time spent on a task. Write machines_heartbeat Update local last-seen and topology metadata for a machine Write machines_register Register a machine in the todos machine registry Write machines_set_primary Set the primary machine Write machines_unarchive Unarchive a machine Write materialize_plan_steps Split plan into ordered step tasks with sequential or parallel execution. Write merge_duplicate_task Merge a duplicate local task into a primary task while preserving comments, dependencies, runs, files, inbox i Write merge_tasks Merge duplicate tasks into a primary record, preserving comments/commits/files and audit history. Write migrate_workflow_states Backfill local workflow state metadata from canonical task statuses. Write move_board_card Move a task or plan card to a target lane or explicit workflow status. Write move_task Re-parent a task to another project and/or task list, preserving its id and history. Write prioritize_task Set a task Write reassign_task Reassign a task to a different agent. Write rebalance_workload Attempt to rebalance task assignments across agents by reassigning from overloaded to underloaded agents. Write record_task_review Record local task review approval, requested changes, or reopen state. Write recover_stale_leases Recover expired/stale task leases and optionally reclaim work for an agent. Write recover_stale_session_handoff Create a local recovery handoff from an agent Write register_agent Register an agent with a distinctive one-word name. Generic/generated names like agent, agent-1, assistant, or Write register_local_machine Register or refresh the local machine in the registry. Write reject_approval_gate Reject a local manual approval checkpoint. Write reject_gate Reject a pending approval gate request. Write release_agent Explicitly release/logout an agent — clears session binding and makes the name immediately available. Call thi Write release_task Unassign a task and mark it pending. Write release_task_lease Release a held task lease. Write rename_agent Rename an agent. Resolve by id or current name. Write renew_task_lease Renew a task lease heartbeat and extend TTL. Write reopen_review_item Reopen a local review queue item for another review pass. Write request_approval Request approval for task start, completion, checkpoint, or plan step. Write request_review_queue Request local review for a task and place it in a review queue. Write request_task_review Request local review for a task. Write reschedule_task Update a task Write resolve_missing_task_findings Resolve open findings absent from the latest loop finding set. Write restore_local_backup Dry-run or apply a local backup restore. Dry-run is the default and reports conflicts before writing. Write resume_focus_session Resume a paused local focus session. Write return_review_item Return a local review queue item with requested changes. Write save_command_alias Save or update a project-local command alias. Write save_search_view Save a local search view for tasks, projects, plans, runs, comments, or all records. Write scan_reminders Scan tasks for due-date and SLA reminders; upsert local reminder records. Write schedule_task Set due date, delayed start, or recurrence rule on a task. Write score_task Score a completed task Write seal_audit_ledger Store a local audit ledger checkpoint for later integrity verification. Write set_agent_run_adapter Create or update a local agent run adapter command. Supports {task_id}, {run_id}, and {agent_id} placeholders. Write set_capacity_profile Create or update a local agent capacity profile. Write set_decision_status Set decision record lifecycle status. Write set_encryption_profile Create or update a local encryption profile. Key material is referenced by environment variable and is never s Write set_focus Focus this agent on a project. All list/search/status tools will default to this project. Write set_local_event_hook Create or update a local event hook for task, plan, run, approval, import, or export events. Write set_policy_pack Create or update a local policy pack for task done gates. Write set_project_agent_role Assign an agent a role on a specific project (client, lead, developer, qa, reviewer, etc.). Per-project roles Write set_release_group Create or update a local roadmap release grouping. Write set_reminder_preferences Update local reminder preferences. Write set_reports_to Set which agent another agent reports to (org chart hierarchy). Write set_review_routing_rule Create or update a local review routing rule for queue and reviewer defaults. Write set_runner_sandbox_profile Create or update a local runner sandbox profile. Write set_secret_safety Add local secret redaction regex patterns or object key names. Write set_task_contract Set local task acceptance criteria, required verification commands, expected artifacts, relevant files, risk, Write set_task_custom_field Set a custom field value on a task. Write set_task_fields Set local labels, priority, severity, owner, area, and custom fields for a task. Write set_task_priority_meta Set numeric priority score (0-100) and/or priority reason on a task. Write set_task_workflow_state Set a task Write set_terminal_notification_rule Create or update a local terminal notification watch rule for task, plan, run, approval, import, or export eve Write set_verification_provider Create or update an optional local verification provider adapter. Providers are local-only and do not call clo Write set_watch_preferences Update local terminal watch preferences. Write set_workspace_trust Create or update a local workspace trust and permission profile. Write snooze_reminder Snooze a reminder until a later ISO datetime. Write start_task Mark a task as in_progress. Uses optimistic locking via version if provided. Write start_task_run Start a local run ledger entry for a task. Optionally claims the task for the agent. Never uploads artifacts o Write steal_task_lease Safely steal a stale or expired task lease. Write stop_focus_session Stop a focus session and log task time when linked to a task. Write supersede_decision_record Create a replacement decision and mark the prior record superseded. Write sync_kg Sync all existing relationships into the knowledge graph edges table. Idempotent. Write sync_todos_md Import then re-export todos.md to keep markdown and database aligned. Write trust_workspace Add (or update) a workspace path as trusted. Write unarchive_agent Restore an archived agent back to active status. Resolve by id or name. Write unarchive_task Restore an archived task back to pending. Write unlock_file Release a file lock. Only the lock holder can release it. Returns true if released. Write unlock_task Release a local task lock. The agent must own the active lock unless omitted for force release. Write unsubscribe_resource Unsubscribe from a resource URI. Write unwatch_task Unsubscribe from notifications for a task. Write update_agent Update an agent Write update_changelog Prepend a generated changelog section to CHANGELOG.md. Write update_comment Edit a comment. Write update_decision_record Update decision record fields (not status). Write update_label Update a label Write update_milestone Update a local roadmap milestone. Write update_plan Update a plan Write update_project Update a project Write update_risk Update a local risk register entry. Write update_roadmap Update a local roadmap. Write update_tag Update a tag Write update_task Plan or execute one deterministic fixture update. Write update_task_list Update a task list Write update_template Update a task template Write update_watch_rule Update a local terminal watch rule. Write upsert_task Create or update a task by stable metadata fingerprint. Metadata is shallow-merged on updates. Write upsert_task_finding Preview or apply an idempotent local finding upsert scoped by task and fingerprint. Write write_template_library Write the bundled local template library to editable JSON files for review or import.
READ 264 tools
Read analyze_branch_work Analyze local git branch vs base: ahead/behind, overlapping files, predicted merge conflicts. Read analyze_dependency_graph Full dependency graph analysis: ready, blocked, cycles, missing deps, critical path. Read bootstrap_project Discover a local workspace and initialize project identity, default task list, and local source metadata. Read build_agent_context_pack Build a deterministic local agent context pack for Codex, Claude Code, Takumi, or generic agents. Returns JSON Read build_handoff_packet Build offline handoff packet with project/plan context, active tasks, blockers, comments, verification, and ne Read build_local_report Build a local JSON or Markdown report from tasks, plans, runs, and verification evidence without hosted analyt Read build_report_export Build read-only local report data (project, plan, run, evidence, roadmap, retrospective). Read bulk_find_tasks_by_files Check multiple file paths at once for task/agent collisions. Returns per-path task list, in-progress count, an Read capture_environment_snapshot Capture a local reproducible environment snapshot with Bun/node versions, package-manager state, git status, c Read check_approval_gate Check whether a local approval gate allows task or run work to proceed. Read check_file_lock Check who holds a lock on a file path. Returns null if unlocked or expired. Read check_local_integrity Check local SQLite quick_check, foreign keys, bridge validation, backup-relevant counts, and orphan rows. Read check_local_notifications Check local due-date, SLA, stale-task, completed-run, and calendar reminder alerts; optionally emit local hook Read check_release_compatibility Check local release compatibility for package metadata, migrations, exports, Bun global install guidance, chan Read check_runner_sandbox Check whether a local runner action is allowed by sandbox and workspace trust policy. Read check_sandbox_command Check if a command is allowed by a local sandbox profile (dry-run explain). Read check_schema_compatibility Check semver/schema compatibility between two schema_version values. Read check_task_done_contract Check whether local task status, verification evidence, artifacts, and review state satisfy the task contract. Read check_task_lock Check local task lock lease status. Read check_workspace_permission Check whether a local command, MCP tool, write path, or env exposure is allowed by the workspace trust profile Read compare_environment_snapshots Compare two local environment snapshot JSON files and report runtime, git, manifest, lockfile, and config hash Read crypto_status Show local encryption key status (never exposes key material). Read decrypt_local_value Decrypt a local encrypted JSON value with the configured profile key. Read decrypt_metadata_fields Decrypt sensitive fields in a metadata object. Read describe_tools Get detailed documentation for a specific tool including all parameters and descriptions. Read discover_local_extensions Discover local extension manifests from config and project .todos folders without installing them. Read discover_workspace Discover local git root, project name, and todos paths for the current workspace. Read encrypt_local_value Encrypt a local JSON value with a configured profile. Read expire_approval_gate Expire a pending local manual approval checkpoint. Read explain_policy_pack Return dry-run explain output for a local policy-pack validation. Read explain_runner_sandbox Return dry-run explain output for a local runner sandbox check. Read export_activity_log Export redacted activity log records as JSON bundle. Read export_agent_reliability_scorecards Export local agent reliability scorecards as deterministic JSON or Markdown without remote reporting. Read export_artifacts Export a local artifacts manifest (JSON) for bridge/import workflows. Does not upload anywhere. Read export_calendar_ics Export local calendar events as deterministic ICS text. Read export_decision_record Export a decision record to local Markdown or JSON. Read export_handoff Export one local handoff as a deterministic JSON bundle. Read export_knowledge_records Export local project knowledge records as deterministic JSON or Markdown. Read export_knowledge_snapshot Export a project knowledge snapshot to local Markdown or JSON. Read export_local_bundle Export local projects/tasks/plans/deps/templates/comments/evidence as a stable JSON bundle for local bridge tr Read export_plan_execution_contract Export portable plan execution contract JSON for hosted bridge. Read export_retrospectives Export stored local retrospectives as deterministic JSON or Markdown. Read export_risk_register Export local risk register entries as deterministic JSON or Markdown. Read export_roadmap Export a local roadmap as JSON bundle or Markdown. Read export_run_replay Export a run record replay bundle to local JSON. Read export_template Export a template as a full JSON object (template + tasks + variables). Useful for sharing or backup. Read export_verification_evidence Export portable verification evidence bundle for a task or run record. Read find_duplicate_tasks Find likely duplicate tasks by title, description, files, commits, and external refs. Read find_path Find paths between two entities in the knowledge graph. Read find_task_by_commit Find which task a git commit SHA is linked to. Supports prefix matching. Read find_tasks_by_file Find which tasks are linked to a specific file path. Shows who Read find_tasks_by_git_ref Find tasks linked to a branch name, PR number, or PR URL. Read format_failure_triage_markdown Format failure triage report as Markdown summary. Read format_goal_handoff Produce JSON or Markdown handoff packet for a /goal plan. Read format_handoff_packet Format a handoff packet as JSON or Markdown. Read format_release_notes_markdown Format a release notes report as Keep a Changelog markdown. Read get_activity_timeline Get chronological activity timeline for an entity. Read get_agent Get agent details by ID or name. Provide one of id or name. Read get_agent_adapter_doc Get full local adapter doc for codex, claude-code, or takumi. Read get_agent_metrics Get performance metrics for an agent: completion rate, speed, confidence, review scores. Read get_agent_reliability_scorecard Get one local-only agent reliability scorecard from completed tasks, failed runs, verification evidence, stale Read get_agent_safe_queue Ordered pending task queue respecting delayed starts and due urgency. Read get_agent_workflow_demo_docs Quickstart docs for the one-command local agent workflow demo. Read get_archived_tasks List archived tasks. Read get_audit_ledger Build a tamper-evident local audit hash chain from task, run, verification, approval, and handoff evidence. Read get_blocked_task_reports List blocked tasks with blockers, stale blockers, and missing dependency refs. Read get_blocked_tasks Get tasks that are blocked by incomplete dependencies. Read get_blocking_tasks Get tasks that are blocking other tasks (incomplete but others depend on them). Read get_board_snapshot Return a JSON snapshot of a local kanban board, including WIP limit state and blocked/ready badges. Read get_bootstrap_status Check whether the current workspace has been bootstrapped. Read get_branch_work_plan_docs Documentation for local branch work plan analysis and safe integration steps. Read get_capability_discovery Search local CLI/MCP capabilities, profiles, and env vars by keyword. Read get_capable_agents Find agents that match given capabilities, sorted by match score. Read get_cli_mcp_parity Get CLI ↔ MCP parity manifest report with matched operations and documented gaps. Read get_cli_reference Manpage-grade CLI reference: command groups, env vars, exit codes. Read get_comments List recent comments for a task. Compact by default; pass detail=full for all comment text. Read get_critical_path Find tasks that block the most downstream work (critical path analysis). Read get_decision_record Get a decision record by id or short ref. Read get_dependency_critical_path Critical path — tasks blocking the most downstream work. Read get_encryption_status Show whether a local encryption profile is locked or unlocked. Read get_failure_triage_report Build local failure triage report for failed tasks, runs, verifications, and agent runs. Read get_feature_manifest Get the local feature manifest: CLI commands, MCP tools, profiles, and env vars. Read get_feature_manifest_docs Quickstart docs for local feature manifest and capability discovery. Read get_file_heat_map Aggregate file edit frequency across all tasks and agents. Returns hottest files with edit count, unique agent Read get_focus Get the current focus for an agent. Read get_goal_status Get /goal plan progress and current step. Read get_health Get system health: task counts by status, active agents, project summary. Read get_idle_focus_prompts Return local idle prompts for active focus sessions. Read get_impact_analysis Analyze what entities are affected if a given entity changes. Traverses the knowledge graph. Read get_inbox_item Get one local inbox intake item by ID or prefix. Read get_json_schema Get JSON Schema definition for an entity type. Read get_knowledge_snapshot Get a stored project knowledge snapshot. Read get_label Get a label and list of tasks using it. Read get_latest_handoff Get the most recent handoff for an agent or project. Read get_leaderboard Get agent leaderboard ranked by composite performance score. Read get_local_snapshot Read one redacted deterministic local snapshot as JSON or Markdown. Uses only local SQLite state. Read get_machine_topology Local machine registry and topology diagnostics: machines, path overrides, agents, stale locks. Read get_my_tasks Get tasks assigned to the calling agent. Supports focus mode scoping. Read get_my_workload Get current workload stats for an agent: in-progress count, tasks due soon, blocked tasks. Read get_next_task Get the best available pending task without claiming it. Read get_onboarding_fixture Return one bundled onboarding fixture as a local bridge bundle. Read get_org_chart Get the global org chart (agent hierarchy + titles). Read get_plan Get a plan with its tasks. Read get_plan_execution_state Get plan execution progress, current step, and ready steps. Read get_planning_forecast Forecast local plan or project completion from estimates, actuals, capacity, and due dates. Read get_project Get full details for a project. Read get_project_org_chart Get org chart scoped to a project — global hierarchy with per-project role overrides merged in. Read get_ready_tasks List pending unblocked tasks ready to claim, ordered by priority. Read get_related_entities Get entities related to a given entity in the knowledge graph. Read get_reminder_preferences Get local reminder preferences (due-soon window, SLA warning lead, desktop notify). Read get_reminder_summary Summary counts for pending, due, snoozed, and fired reminders. Read get_resource_changes Poll for resource URIs with task changes since timestamp. Read get_resource_snapshot Fetch a fresh local resource snapshot with stale_after metadata. Read get_review_queue Get tasks that need review: requires_approval but unapproved, or low confidence completions. Read get_roadmap_summary Get computed local roadmap progress, milestone, release, and blocker summary. Read get_run_record Get a local run record by ID. Read get_scheduling_summary Local scheduling summary: due, overdue, stale, delayed, recurring, next claimable. Read get_secret_safety Show local secret redaction configuration. Read get_shell_completion Generate bash, zsh, or fish completion script for todos CLI. Read get_sla_breaches List unfinished local tasks that are overdue or past their SLA minutes and should be escalated. Read get_stale_task_report Report stale in_progress tasks with minutes stale. Read get_stale_tasks Get tasks that haven Read get_status Get queue status summary, or pass task_id for a task Read get_tag Get a tag and list of tasks using it. Read get_task Read one Todos task by its stable identifier. Read get_task_commits Get all git commits linked to a task. Read get_task_contract Get local task contract and review state. Read get_task_dependencies Get full dependency tree for a task. Read get_task_fields Export labels, custom fields, and priority metadata for a task. Read get_task_gate_status Get blocked/ready status for task start and completion gates. Read get_task_git_refs Get branches and pull requests linked to a task. Read get_task_list Get a task list with its tasks. Read get_task_relationships Get all semantic relationships for a task. Read get_task_run_ledger Get a local run ledger with events, commands, files, and artifact metadata. Read get_task_traceability Get aggregated git traceability report for a task (commits, branches, PRs, CI, releases). Read get_task_watchers List agents watching a task. Read get_tasks_changed_since List tasks changed since an ISO timestamp. Read get_time_report Get time tracking report: actual vs estimated minutes for completed tasks. Read get_unlock_impact Show which dependent tasks would become ready if a task completes. Read get_usage_ledger Get an aggregate local usage ledger for tasks, projects, runs, commands, costs, durations, storage, and simula Read get_verification_provider_capabilities Describe a local verification provider Read get_watch_preferences Get local terminal watch preferences (interval, bell, quiet, desktop notify). Read get_watch_status Summary of watch cursor, rules, and preferences. Read get_workspace_trust Show local trust status for a workspace path. Read inspect_git_commit Inspect a local git commit (message, author, files, branch). Read inspect_local_extension Validate a local extension manifest, directory, or offline bundle without installing it. Read list_access_profiles List local access profiles (read_only, agent_safe, minimal, standard, full, admin). Read list_active_files Return all files linked to in-progress tasks across all agents — the bird Read list_active_leases List active task leases, optionally filtered by agent. Read list_activity List append-only activity log records with optional filters. Read list_agent_adapter_docs List first-party local adapter docs for Codex, Claude Code, and Takumi. Read list_agent_adapters List locally configured agent run adapters (stdio, tmux, script). Read list_agent_run_adapters List configured local agent run adapters. Read list_agent_run_queue List local agent run dispatch queue entries. Read list_agent_runs List local agent runs with optional status/adapter filters. Read list_agents List all registered agents. By default shows only active agents — set include_archived to see archived ones to Read list_approval_gates List local approval gates for a task. Read list_artifacts List local artifacts for an entity. Read list_audit_ledger_checkpoints List sealed local audit ledger checkpoints. Read list_boards List local task and plan kanban boards. Read list_calendar_events List local calendar events derived from tasks, SLA thresholds, runs, and local calendar items. Read list_capacity_profiles List local planning capacity profiles. Read list_command_aliases List project-local saved command aliases from .todos/aliases.json. Read list_comments List all comments on a task. Read list_decision_records List ADR-style decision records with optional filters. Read list_dispatches List dispatch history with optional status filter. Shows target, task count, timing, and any errors. Read list_encryption_profiles List local encryption profiles for secure fields and exports. Read list_file_locks List all active file locks. Optionally filter by agent_id. Read list_focus_sessions List local focus sessions with optional task, plan, run, agent, and status filters. Read list_handoffs List local session handoffs, optionally only unread for an agent. Read list_inbox_items List local inbox intake items. Read list_json_schemas List versioned JSON schemas for tasks, projects, plans, runs, evidence, handoffs, bundles, and MCP responses. Read list_knowledge_records List local project knowledge records with optional filters. Read list_knowledge_snapshots List stored project knowledge snapshots. Read list_labels List all labels. Read list_local_event_hooks List configured local event hooks and automation triggers. Read list_local_extensions List installed local workflow extensions. Read list_local_report_types List stable local report sections available for agent-native planning, runs, and verification summaries. Read list_local_snapshots List stable local snapshot resources for projects, tasks, plans, runs, dependencies, events, and evidence. Read list_my_tasks Alias for get_my_tasks. Read list_onboarding_fixtures List bundled local onboarding fixtures. The fixtures are deterministic, redacted, local-only, and require no n Read list_pending_approvals List pending approval gate requests. Read list_plans List a bounded set of Todos plans, optionally scoped to a project. Read list_policy_packs List locally configured policy packs for task done gates. Read list_project_agent_roles List all agent role assignments for a project. Read list_projects List a bounded set of Todos projects. Read list_reminders List local notification reminders (due-date, SLA, custom). Read list_retrospectives List stored local retrospectives with optional project, plan, and agent filters. Read list_review_queue List local review queue items with explicit queue, reviewer, claim, return, and approval state. Read list_review_routing_rules List local review routing rules. Read list_risks List local risk register entries with optional project, plan, task, owner, status, and severity filters. Read list_roadmaps List local roadmaps. Read list_run_records List local run records with optional filters. Read list_runner_sandbox_profiles List local runner sandbox profiles. Read list_sandbox_profiles List local runner sandbox profiles with command allow/deny lists. Read list_saved_views List saved search views. Read list_search_views List local saved search views. Read list_secret_patterns List built-in secret detection patterns (denylist). Read list_tags List all distinct task tags in use, with task counts. Read list_task_files List all files linked to a task. Read list_task_findings List compact local findings with bounded output. Read list_task_lists List all task lists. Read list_task_runs List local run ledger entries, optionally scoped to a task. Read list_tasks List a bounded set of Todos tasks using read-only filters. Read list_template_library List bundled marketplace-free template library (local-only). Read list_templates List all task templates Read list_terminal_notification_rules List configured local terminal notification watch rules. Read list_user_scaffolds List user-authored local scaffolds. Read list_verification_providers List configured local verification provider adapters. Read list_verification_records List stored verification evidence records. Read list_watch_rules List local terminal watch rules for task/plan/run/approval events. Read list_workflow_states List local project workflow states mapped onto canonical task statuses. Read list_workspace_trust_profiles List local workspace trust and permission profiles. Read machines_list List all registered machines Read machines_topology Show local machine topology diagnostics without network probing Read migration_dry_run List pending SQLite migrations without applying them. Read notify_upcoming_deadlines Get tasks with deadlines approaching within the threshold. Good for reminders. Read parse_mentions Parse @file, @symbol, @task, @plan, @run, git refs, and URLs from text without resolving. Read patrol_tasks Scan for task issues: stuck tasks, low-confidence completions, orphaned tasks, zombie-blocked tasks, and pendi Read pause_focus_session Pause an active local focus session. Read poll_local_snapshots Poll local snapshots and return only resources with cursors newer than the supplied ISO cursor. Read poll_watch_notifications Poll local DB for watch events and emit terminal notifications. Read preview_bundle_sync Preview sync conflicts between a JSON bundle and local database. Read preview_inbox_intake Preview local inbox intake (GitHub issue, CI log, feedback, error paste, file) with dedupe and redaction. Read preview_issue_import Preview importing GitHub, Linear, or Jira issues from local JSON export files with dedupe. Read preview_natural_language_intake Preview or apply deterministic local natural-language task intake without hosted model calls. Read preview_nl_intake Preview natural-language task intake with local parsing, dedupe, and redaction (dry-run). Read preview_retention_cleanup Preview local retention cleanup candidates for comments, runs, verification evidence, and expired artifact fil Read preview_template Preview a template without creating tasks. Shows resolved titles (variables substituted), dependencies, and pr Read preview_template_library Preview a bundled template with variable substitution (no tasks created). Read query_tasks_by_fields Query tasks by local labels, priority, severity, owner, area, and custom fields. Read query_tasks_by_workflow_state Query tasks by local workflow state while preserving canonical task statuses. Read read_handoff Read one local handoff by ID or prefix. Read read_task Read one deterministic fixture task. Read request_input Request deterministic clarification. Read resolve_command_query Resolve natural query shortcut or @alias to todos argv with explain/dry-run output. Read resolve_mention Resolve a single mention (@file, @symbol, task/plan/run ref, branch, commit, PR, URL) to a local link and snip Read resolve_mentions Resolve local file, line, symbol, git ref, plan, run, task, and agent mentions without hosted lookups. Read resolve_mentions_in_text Parse and resolve all mentions in text. Snippets redacted by default. Read resource_diagnostics Show MCP resource subscription diagnostics. Read run_search_view Run a local saved search view and return stable JSON results. Read scan_file_for_secrets Scan a local file for secret patterns before release or export. Read scan_secret_text Scan text for secret-like values and return counts without exposing values. Read scan_text_for_secrets Scan text for secret patterns (API keys, tokens, private keys). Returns redacted output — never raw secrets. Read score_plan_health Score a plan Read score_project_health Score a project Read search_knowledge_records Search local project knowledge records by title, body, decisions, rationale, and tags. Read search_tasks Full-text search across task titles and descriptions. Read search_tools Search available MCP tools by keyword. Returns matching tool names and descriptions. Read standup Get a standup report: in-progress tasks, completed yesterday, and blockers for an agent. Read subscribe_resource Subscribe to local MCP resource change notifications (poll via get_resource_changes). Read suggest_agent_name Get available Roman/Greek-style agent names for a project. Use these instead of generic generated names. Read task_context Get compact context for a task by default: details, dependencies, relationships, comments, files, commits, and Read template_history Show version history of a template. Each update creates a snapshot of the previous state. Read todos_inbox Get unassigned tasks (GTD inbox) — tasks with no assignee, not yet started. Read todos_retro Post-completion retrospective: stats on completed tasks, low-confidence completions, avg time vs estimate, and Read unified_search Local unified search across tasks, projects, plans, comments, and runs. Read validate_bundle Validate a todos.bundle.v1 JSON bundle structure. Read validate_policy_pack Validate a task against a local policy pack (done gates). Use dry_run to explain without blocking. Read validate_schema_payload Validate a JSON payload against a published todos schema. Read verify_audit_ledger Verify current local evidence against a sealed audit ledger checkpoint. Read verify_local_backup Verify a local backup bundle checksum, manifest counts, bridge schema compatibility, and current SQLite integr Read verify_task_run_artifacts Verify locally stored run artifact content against recorded checksums. Read watch_task Subscribe to notifications for a task.
EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

UnClick 1662 tools
adminautomation
Delx Mcp A2a 1082 tools
adminautomation
Delx Protocol — Agent Recovery & Continuity 1076 tools
adminautomation
Nodebench 824 tools
adminautomation
MCP Framework Personal 811 tools
adminautomation
Delx MCP Server 740 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Eda Agent 726 tools
adminautomation
FAQ

Questions about Todos

Can an AI agent delete data through the Todos MCP server? +

Yes. The Todos server exposes 37 destructive tools including apply_retention_cleanup, bulk_delete_tasks, cancel_agent_run. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Todos? +

The Todos server has 197 write tools including acknowledge_handoff, acquire_task_lease, add_artifact. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Todos.

How many tools does the Todos MCP server expose? +

528 tools across 4 categories: Destructive, Execute, Read, Write. 264 are read-only. 264 can modify, create, or delete data.

How do I enforce a policy on Todos? +

Register the Todos MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Todos tool call.

Deterministic rules across all 528 Todos tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TODOS →

Instant setup, no code required.

528 Todos tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Todos's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.