TaskWarrior MCP Server

Command LineTypeScript

Manage your TaskWarrior tasks directly through AI assistants

Available Tools

get_next_tasks

Get a list of all pending tasks with optional filtering by project and tags

projecttags

add_task

Add a new task to TaskWarrior with description, due date, priority, project, and tags

descriptionduepriorityprojecttags

mark_task_done

Mark a task as completed using its identifier (ID or UUID)

identifier

TaskWarrior MCP provides a seamless interface between AI assistants and the popular TaskWarrior command-line task management tool. It allows you to view, filter, add, and complete tasks in your TaskWarrior database through natural language conversations with AI assistants. This integration enables powerful task management workflows where you can ask about pending tasks, create new tasks with priorities and due dates, and mark tasks as complete - all without leaving your conversation with the AI assistant. The server acts as a bridge between the AI and your local TaskWarrior installation.

Overview

TaskWarrior MCP Server allows AI assistants to interact with your local TaskWarrior installation, enabling you to manage your tasks through natural language conversations. This server implements the Model Context Protocol (MCP) to provide a bridge between AI assistants and the TaskWarrior command-line tool.

Prerequisites

Before installing the TaskWarrior MCP Server, ensure you have:

TaskWarrior installed and configured on your system
Node.js and npm installed

Installation

To install the TaskWarrior MCP Server globally, run:

npm install -g mcp-server-taskwarrior

Configuration

For Claude Desktop

To use TaskWarrior MCP with Claude Desktop, add the following to your claude_desktop_config.json file:

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

For Other AI Assistants

For other AI assistants that support MCP, you'll need to configure them to use the TaskWarrior MCP Server. Refer to your specific AI assistant's documentation for instructions on adding MCP servers.

Usage Examples

Once configured, you can interact with TaskWarrior through natural language. Here are some example prompts you can use with your AI assistant:

"What are my current work tasks?"
"Show me all tasks with the 'urgent' tag"
"Add a new task: Call my sister by tomorrow with high priority"
"Mark the task about calling my sister as complete"
"What tasks are due this week?"
"Create a new task for the 'home' project with a medium priority"

Important Notes

The server currently uses task IDs which can change when tasks are added or removed. Future versions will use the more stable UUID identifiers.
All operations are performed on your local TaskWarrior database, so ensure you have proper backups.
The server needs to be running for the AI assistant to interact with TaskWarrior.

Troubleshooting

If you encounter issues:

Ensure TaskWarrior is properly installed and configured on your system
Verify that the task command works correctly in your terminal
Check that the MCP server is properly configured in your AI assistant
Look for error messages in the terminal where the MCP server is running