Atlas / MCP servers / awwaiid / TaskWarrior

TaskWarriorSAFE

mcp/awwaiid/taskwarrior-1

MCP Server for TaskWarrior!

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
3 2r · 1w · 0d
Transport
stdio
License
MIT
Stars
51
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Node.js server implementing Model Context Protocol (MCP) for TaskWarrior operations.

Features

  • View pending tasks
  • Filter tasks by project and tags
  • Add new tasks with descriptions, due dates, priorities, projects and tags
  • Mark tasks as complete

Note: This runs your local task binary, so TaskWarrior needs to be installed and configured!

[!WARNING] This currently uses task id which is an unstable identifier; taskwarrior sometimes renumbers tasks when new ones are added or removed. In the future this should be more careful, using task UUID instead.

API

Tools

  • get_next_tasks
  • Get a list of all pending tasks
  • Optional filters:
  • project: Filter by project name
  • tags: Filter by one or more tags
  • add_task
  • Add a new task to TaskWarrior
  • Required:
  • description: Task description text
  • Optional:
  • due: Due date (ISO timestamp)
  • priority: Priority level ("H", "M", or "L")
  • project: Project name (lowercase with dots)
  • tags: Array of tags (lowercase)
  • mark_task_done
  • Mark a task as completed
  • Required:
  • identifier: Task ID or UUID

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

{
"mcpServers": {
"taskwarrior": {
"command": "npx",
"args": [
"-y",
"mcp-server-taskwarrior"
]
}
}
}

Installation

npm install -g mcp-server-taskwarrior

Make sure you have TaskWarrior (task) installed and configured on your system.

Example usage ideas:

  • What are my current work tasks?
  • Executes: task project:work next
  • TODO: Call my sister (high priority)
  • Executes: task add priority:H Call my sister
  • OK, I've called my si
Read from source at commit ba1398db3d5bOBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add mcp-server-taskwarrior -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-server-taskwarrior": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (3)

2 read · 1 write · 0 destructive.

ToolRiskDescription
add_taskwriteAdd a new task
get_next_tasksreadGet a list of all pending tasks
mark_task_donereadMark a task as done (completed)
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (1)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
diff, glob, minimatch, zod-to-json-schema, @types/diff, @types/minimatch, @types/node, shx
Why it matters. 9 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha ba1398db3d5bfull audit observations/trust-audit/mcp-server/awwaiid__taskwarrior-1.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08ba1398db3d5bSAFEB89first audit
06

Questions

What is the TaskWarrior MCP server?

MCP Server for TaskWarrior!

What tools does TaskWarrior expose?

3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is TaskWarrior safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does TaskWarrior need?

No credential environment variables were found in its source, so it appears to need none.

How does TaskWarrior run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-server-taskwarrior at 1.0.1.

How current is this page?

The grade is for one exact copy of the source (ba1398db3d5b), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement