Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Taskwarrior Ai

FreeNot checked

An AI-native Taskwarrior bridge that provides natural language task management for Claude Code and other AI systems, integrating with existing Taskwarrior infra

GitHubEmbed

About

An AI-native Taskwarrior bridge that provides natural language task management for Claude Code and other AI systems, integrating with existing Taskwarrior infrastructure.

README

An AI-native Taskwarrior bridge that provides natural language task management for Claude Code and other AI systems. This MCP (Model Context Protocol) server extends Taskwarrior with context-aware, natural language capabilities while building on top of the existing Taskwarrior infrastructure.

Features

  • Natural Language Processing: Convert everyday language into Taskwarrior commands
  • Project Context Awareness: Automatically detects current project/ticket context
  • Ticket Integration: Sync tasks from ticket checklists (supports .tickets/ directory structure)
  • Eisenhower Matrix: Organize tasks by urgency and importance
  • Smart Task Addition: Intelligently parse priorities, due dates, projects, and tags
  • Shareable & Versioned: Configuration can be tracked in Git

Installation

Prerequisites

  1. Install Taskwarrior (if not already installed):
brew install task
  1. Install Node.js (v20 or later):
brew install node

Setup

  1. Clone the repository:
git clone https://github.com/storypixel/mcp-taskwarrior-ai.git
cd mcp-taskwarrior-ai
  1. Install dependencies:
npm install
  1. Build the project:
npm run build

Integration with Claude Code

Add the server to your Claude Code MCP configuration:

  1. Open your Claude Code settings
  2. Add to MCP servers:
{
  "mcpServers": {
    "taskwarrior": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/mcp-taskwarrior-ai/dist/index.js"],
      "env": {}
    }
  }
}

Or using the Claude CLI:

claude mcp add taskwarrior -s project -- node /path/to/mcp-taskwarrior-ai/dist/index.js

Usage

Natural Language Commands

The bridge understands natural language for task management:

  • Adding tasks: "add fix the login bug", "create task for code review", "todo implement caching"
  • Listing tasks: "show all tasks", "what should I work on next", "list urgent tasks", "show tasks for today"
  • Completing tasks: "mark task 5 as done", "complete task 1", "finish the review task"
  • Context queries: "where am I", "what's my current project", "show current context"

Available Tools

task_natural

Execute Taskwarrior commands using natural language.

{
  query: "add fix the authentication bug with high priority"
}

task_smart_add

Add tasks with structured metadata:

{
  description: "Implement user authentication",
  project: "myheb-android",
  priority: "H",
  due: "tomorrow",
  tags: ["security", "auth"]
}

task_ticket_sync

Import tasks from a ticket's checklist:

{
  ticket: "DRX-12345"
}

task_eisenhower

Get tasks organized by Eisenhower Matrix quadrants.

task_where_am_i

Get current context and suggested next actions based on project state.

task_context_set

Set the current project/context for all task operations:

{
  context: "DRX-12345"
}

task_raw

Execute raw Taskwarrior commands for advanced users:

{
  command: "modify 1 priority:H +urgent"
}

Project Context Integration

The bridge automatically detects project context using:

  1. .taskproject file - If present, defines the project name for Taskwarrior
  2. Git repository name - Falls back to the repo name from git
  3. Directory name - Uses current directory name if not in git

To override project detection, create a .taskproject file:

echo "my-project-name" > .taskproject

This is useful when one workspace manages tasks for another project.

The bridge also detects:

  • Current Git branch (for ticket context)
  • Task state from .task-state.json
  • Ticket tasks from .tickets/<ticket>/mr-checklist.md

Architecture

┌─────────────────┐
│  Claude Code    │
│   or AI Agent   │
└────────┬────────┘
         │ Natural Language
         ▼
┌─────────────────┐
│  MCP Server     │
│  - NLP Parser   │
│  - Context Mgr  │
└────────┬────────┘
         │ Taskwarrior Commands
         ▼
┌─────────────────┐
│   Taskwarrior   │
│   (task CLI)    │
└─────────────────┘

Development

Running in Development Mode

npm run dev

Testing

Run the test script to verify the server is working:

node test.js

Building

npm run build

Configuration

The server uses your existing Taskwarrior configuration (~/.taskrc). You can customize Taskwarrior settings as usual.

Context Detection

The bridge uses the current working directory and automatically detects project context. No hardcoded paths or specific project names are used.

Ticket Integration

Place ticket tasks in:

.tickets/
└── DRX-12345/
    ├── context.md       # Ticket context
    └── mr-checklist.md  # Tasks as checklist items

Format for mr-checklist.md:

- [ ] Update unit tests
- [ ] Add documentation
- [ ] Run linting

Prompts

The server includes built-in prompts:

Daily Review

Get a prioritized plan for the day including today's tasks, urgent items, and recommended next actions.

Weekly Planning

Organize tasks for the week ahead with active projects overview.

Troubleshooting

"Cannot proceed without rc file"

Initialize Taskwarrior:

task version

Context not detected

Ensure you're in a project directory or have .task-state.json in your workspace.

Ticket sync not finding tasks

Verify .tickets/<ticket>/mr-checklist.md exists and contains checkbox items.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT

Author

storypixel

Acknowledgments

Built on top of Taskwarrior - the command-line task management tool.

from github.com/storypixel/mcp-taskwarrior-ai

Installing Taskwarrior Ai

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/storypixel/mcp-taskwarrior-ai

FAQ

Is Taskwarrior Ai MCP free?

Yes, Taskwarrior Ai MCP is free — one-click install via Unyly at no cost.

Does Taskwarrior Ai need an API key?

No, Taskwarrior Ai runs without API keys or environment variables.

Is Taskwarrior Ai hosted or self-hosted?

Self-hosted: the server runs locally on your machine via the install command above.

How do I install Taskwarrior Ai in Claude Desktop, Claude Code or Cursor?

Open Taskwarrior Ai on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Taskwarrior Ai with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All development MCPs