// SCAN REPORT

Taskwarrior MCP Server

22 tools. 11 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

11 can modify or destroy data

11 read-only

22 tools total

Community server · catalogue entry verified 29/06/2026

How to control Taskwarrior MCP Server ↓

TOOL MAP

What Taskwarrior MCP Server exposes to your agents

Read (11) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Taskwarrior MCP Server tools

Destructive · High taskwarrior_delete Task deletion is irreversible and removes data permanently from the task management system. Execute · Medium taskwarrior_start Starting a task in Taskwarrior typically transitions its state and may trigger side effects like updating timestamps or triggering dependent tasks. Write · Low taskwarrior_stop This tool modifies the state of a task by stopping the active timer/tracking on it. Write · Medium taskwarrior_add This tool creates new tasks in Taskwarrior, which is a reversible write operation.

11 of Taskwarrior MCP Server's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Taskwarrior MCP Server

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

Deny destructive operations

{
  "taskwarrior_delete": {
    "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

{
  "taskwarrior_add": {
    "limits": [
      {
        "counter": "taskwarrior_add_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "taskwarrior_blocked": {
    "limits": [
      {
        "counter": "taskwarrior_blocked_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Taskwarrior MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TASKWARRIOR →

Instant setup, no code required.

FULL CATALOGUE

All 22 Taskwarrior MCP Server tools

DESTRUCTIVE 1 tools

Destructive taskwarrior_delete taskwarrior_delete

EXECUTE 1 tools

Execute taskwarrior_start taskwarrior_start

WRITE 8 tools

Write taskwarrior_add taskwarrior_add Write taskwarrior_annotate taskwarrior_annotate Write taskwarrior_complete taskwarrior_complete Write taskwarrior_context taskwarrior_context Write taskwarrior_modify taskwarrior_modify Write taskwarrior_stop Stop working on a task. Write taskwarrior_triage taskwarrior_triage Write taskwarrior_undo Undo the last Taskwarrior operation.

READ 11 tools

Read taskwarrior_blocked taskwarrior_blocked Read taskwarrior_bulk_get taskwarrior_bulk_get Read taskwarrior_dependencies taskwarrior_dependencies Read taskwarrior_get taskwarrior_get Read taskwarrior_list taskwarrior_list Read taskwarrior_overview taskwarrior_overview Read taskwarrior_project_summary taskwarrior_project_summary Read taskwarrior_projects taskwarrior_projects Read taskwarrior_ready taskwarrior_ready Read taskwarrior_summary taskwarrior_summary Read taskwarrior_tags taskwarrior_tags

OTHER 1 tools

Other taskwarrior_suggest taskwarrior_suggest

EXPLORE

Related servers

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

FAQ

Questions about Taskwarrior MCP Server

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

Yes. The Taskwarrior MCP Server server exposes 1 destructive tools including taskwarrior_delete. 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 Taskwarrior MCP Server? +

The Taskwarrior MCP Server server has 8 write tools including taskwarrior_add, taskwarrior_annotate, taskwarrior_complete. 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 Taskwarrior MCP Server.

How many tools does the Taskwarrior MCP Server MCP server expose? +

22 tools across 4 categories: Destructive, Execute, Read, Write. 11 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Taskwarrior MCP Server? +

Register the Taskwarrior MCP Server 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 Taskwarrior MCP Server tool call.

Deterministic rules across all 22 Taskwarrior MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TASKWARRIOR →

Instant setup, no code required.

22 Taskwarrior MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Taskwarrior MCP Server'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 →