Task Master MCP server for AI agents

Taskmaster is an AI-powered task management system designed to streamline AI-driven development workflows. It integrates with your editor and AI chat to help organize, track, and implement development tasks efficiently.

Installation

MCP Installation (Recommended)

MCP (Model Control Protocol) allows you to run Taskmaster directly from your editor.

Step 1: Add MCP Configuration

Choose the appropriate configuration path based on your editor:

For Cursor & Windsurf & Q Developer CLI

{
  "mcpServers": {
    "task-master-ai": {
      "command": "npx",
      "args": ["-y", "task-master-ai"],
      "env": {
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE"
        // Add other API keys as needed
      }
    }
  }
}

For VS Code

{
  "servers": {
    "task-master-ai": {
      "command": "npx",
      "args": ["-y", "task-master-ai"],
      "env": {
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE"
        // Add other API keys as needed
      },
      "type": "stdio"
    }
  }
}

Step 2: Enable Taskmaster MCP (Cursor only)

In Cursor, open Settings (Ctrl+Shift+J), click on the MCP tab, and enable task-master-ai using the toggle.

Step 3: Initialize Taskmaster

In your editor's AI chat pane, type:

Initialize taskmaster-ai in my project

Command Line Installation

If you prefer using the command line:

# Install globally
npm install -g task-master-ai

# OR install locally in your project
npm install task-master-ai

Then initialize:

# If installed globally
task-master init

# If installed locally
npx task-master init

Usage

Setting Up Your Project

Initialize Taskmaster in your chat:
```
Initialize taskmaster-ai in my project
```
Create a PRD (Product Requirements Document):
- For new projects: Create it at .taskmaster/docs/prd.txt
- For existing projects: Use scripts/prd.txt or migrate with task-master migrate
- An example template is available at .taskmaster/templates/example_prd.txt

Configure Models (optional):

Change the main model to claude-3-opus-20240229

Change the main, research and fallback models to claude-3-sonnet-20240229, pplx-7b-online, gpt-4o respectively

Common Chat Commands

Use these phrases in your AI chat:

Parse requirements: Can you parse my PRD at scripts/prd.txt?
Plan next step: What's the next task I should work on?
Implement a task: Can you help me implement task 3?
View multiple tasks: Can you show me tasks 1, 3, and 5?
Expand a task: Can you help me expand task 4?
Research fresh information: Research the latest best practices for implementing JWT authentication with Node.js
Research with context: Research React Query v5 migration strategies for our current API implementation in src/api.js

Command Line Usage

If using Taskmaster from the command line:

# Parse a PRD and generate tasks
task-master parse-prd your-prd.txt

# List all tasks
task-master list

# Show the next task to work on
task-master next

# Show specific tasks
task-master show 1,3,5

# Research with project context
task-master research "What are the latest best practices for JWT authentication?"

# Move tasks between tags
task-master move --from=5 --from-tag=backlog --to-tag=in-progress

# Generate task files
task-master generate

Optimizing Performance

You can optimize Taskmaster's performance by configuring the tools it loads through the TASK_MASTER_TOOLS environment variable:

Mode	Tools	Context Usage	Use Case
`all` (default)	36	~21,000 tokens	Complete feature set
`standard`	15	~10,000 tokens	Common operations
`core`	7	~5,000 tokens	Essential workflow
`custom`	Variable	Variable	Specific tools

Add this to your MCP configuration:

"env": {
  "TASK_MASTER_TOOLS": "standard",
  // other environment variables
}

Troubleshooting

If task-master init doesn't respond, try:

node node_modules/claude-task-master/scripts/init.js

Or clone the repository and run:

git clone https://github.com/eyaltoledano/claude-task-master.git
cd claude-task-master
node scripts/init.js

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "taskmaster-ai" '{"command":"npx","args":["-y","--package=task-master-ai","task-master-ai"],"env":{"ANTHROPIC_API_KEY":"YOUR_ANTHROPIC_API_KEY_HERE","PERPLEXITY_API_KEY":"YOUR_PERPLEXITY_API_KEY_HERE","OPENAI_API_KEY":"YOUR_OPENAI_KEY_HERE","GOOGLE_API_KEY":"YOUR_GOOGLE_KEY_HERE","MISTRAL_API_KEY":"YOUR_MISTRAL_KEY_HERE","OPENROUTER_API_KEY":"YOUR_OPENROUTER_KEY_HERE","XAI_API_KEY":"YOUR_XAI_KEY_HERE","AZURE_OPENAI_API_KEY":"YOUR_AZURE_KEY_HERE","OLLAMA_API_KEY":"YOUR_OLLAMA_API_KEY_HERE"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "taskmaster-ai": {
            "command": "npx",
            "args": [
                "-y",
                "--package=task-master-ai",
                "task-master-ai"
            ],
            "env": {
                "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
                "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
                "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
                "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
                "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
                "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
                "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
                "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
                "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "taskmaster-ai": {
            "command": "npx",
            "args": [
                "-y",
                "--package=task-master-ai",
                "task-master-ai"
            ],
            "env": {
                "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
                "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
                "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
                "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
                "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
                "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
                "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
                "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
                "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect