Taskwarrior MCP Server

An MCP (Model Context Protocol) server that enables AI assistants to interact with Taskwarrior, the powerful command-line task management tool.

Features

• Full Taskwarrior Integration: List, create, modify, complete, and delete tasks

• Project & Tag Management: Organize tasks with projects and tags

• Annotations: Add notes and context to tasks

• Filtering: Use Taskwarrior's powerful filter expressions

• Multiple Output Formats: Get responses in Markdown or JSON

• Agent Intelligence: Smart suggestions, dependency analysis, triage tools

Prerequisites

• Python 3.10 or higher

• Taskwarrior installed and available in your PATH

Installing Taskwarrior

# macOS
brew install task

# Ubuntu/Debian
sudo apt install taskwarrior

# Fedora
sudo dnf install task

# Arch Linux
sudo pacman -S task

Installation

From PyPI (recommended)

pip install taskwarrior-mcp

From Source

git clone https://github.com/yourusername/taskwarrior-mcp.git
cd taskwarrior-mcp
pip install -e .

Verifying Installation

# Check the version
python -c "from taskwarrior_mcp import __version__; print(__version__)"

# Or run the server directly
taskwarrior-mcp --help

Configuration

See the examples/ directory for complete configuration files.

Claude Desktop

Add to your Claude Desktop configuration file:

{
  "mcpServers": {
    "taskwarrior": {
      "command": "taskwarrior-mcp"
    }
  }
}

Claude Code CLI

Add to your ~/.claude/settings.json:

{
  "mcpServers": {
    "taskwarrior": {
      "command": "taskwarrior-mcp"
    }
  }
}

Using uvx (no installation required)

{
  "mcpServers": {
    "taskwarrior": {
      "command": "uvx",
      "args": ["taskwarrior-mcp"]
    }
  }
}

Advanced Configuration

Use environment variables to customize Taskwarrior behavior:

{
  "mcpServers": {
    "taskwarrior": {
      "command": "taskwarrior-mcp",
      "env": {
        "TASKRC": "/path/to/custom/.taskrc",
        "TASKDATA": "/path/to/custom/.task"
      }
    }
  }
}

See examples/ for more configurations including multiple databases.

Available Tools

Core Task Management

Agent Intelligence Tools

Usage Examples

Once configured, you can interact with Taskwarrior through your AI assistant:

Basic Task Management

• "What tasks do I have?"

• "Add a task to review the quarterly report with high priority"

• "Show me all tasks in the work project"

• "Complete task 5"

• "What's due this week?"

Agent Intelligence

• "What should I work on next?" - Uses taskwarrior_suggest for smart recommendations

• "What tasks are ready to start?" - Uses taskwarrior_ready for unblocked tasks

• "What's blocking my progress?" - Uses taskwarrior_blocked and taskwarrior_dependencies

• "Any tasks I've forgotten about?" - Uses taskwarrior_triage for stale/orphaned tasks

• "Give me context on task 5" - Uses taskwarrior_context for rich task details

Development

Setup

git clone https://github.com/yourusername/taskwarrior-mcp.git
cd taskwarrior-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

Running Tests

pytest

Code Quality

# Format code
black .
ruff check --fix .

# Type checking
mypy taskwarrior_mcp.py

License

MIT License - see LICENSE for details.

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines on:

• Development setup

• Commit message conventions (Conventional Commits)

• Pull request process

• Code style requirements