* feat(tasks): Fix critical tag corruption bug in task management - Fixed missing context parameters in writeJSON calls across add-task, remove-task, and add-subtask functions - Added projectRoot and tag parameters to prevent data corruption in multi-tag environments - Re-enabled generateTaskFiles calls to ensure markdown files are updated after operations - Enhanced add_subtask MCP tool with tag parameter support - Refactored addSubtaskDirect function to properly pass context to core logic - Streamlined codebase by removing deprecated functionality This resolves the critical bug where task operations in one tag context would corrupt or delete tasks from other tags in tasks.json. * feat(task-manager): Enhance addSubtask with current tag support - Added `getCurrentTag` utility to retrieve the current tag context for task operations. - Updated `addSubtask` to use the current tag when reading and writing tasks, ensuring proper context handling. - Refactored tests to accommodate changes in the `addSubtask` function, ensuring accurate mock implementations and expectations. - Cleaned up test cases for better readability and maintainability. This improves task management by preventing tag-related data corruption and enhances the overall functionality of the task manager. * feat(remove-task): Add tag support for task removal and enhance error handling - Introduced `tag` parameter in `removeTaskDirect` to specify context for task operations, improving multi-tag support. - Updated logging to include tag context in messages for better traceability. - Refactored task removal logic to streamline the process and improve error reporting. - Added comprehensive unit tests to validate tag handling and ensure robust error management. This enhancement prevents task data corruption across different tags and improves the overall reliability of the task management system. * feat(add-task): Add projectRoot and tag parameters to addTask tests - Updated `addTask` unit tests to include `projectRoot` and `tag` parameters for better context handling. - Enhanced test cases to ensure accurate expectations and improve overall test coverage. This change aligns with recent enhancements in task management, ensuring consistency across task operations. * feat(set-task-status): Add tag parameter support and enhance task status handling - Introduced `tag` parameter in `setTaskStatusDirect` and related functions to improve context management in multi-tag environments. - Updated `writeJSON` calls to ensure task data integrity across different tags. - Enhanced unit tests to validate tag preservation during task status updates, ensuring robust functionality. This change aligns with recent improvements in task management, preventing data corruption and enhancing overall reliability. * feat(tag-management): Enhance writeJSON calls to preserve tag context - Updated `writeJSON` calls in `createTag`, `deleteTag`, `renameTag`, `copyTag`, and `enhanceTagsWithMetadata` to include `projectRoot` for better context management and to prevent tag corruption. - Added comprehensive unit tests for tag management functions to ensure data integrity and proper tag handling during operations. This change improves the reliability of tag management by ensuring that operations do not corrupt existing tags and maintains the overall structure of the task data. * feat(expand-task): Update writeJSON to include projectRoot and tag context - Modified `writeJSON` call in `expandTaskDirect` to pass `projectRoot` and `tag` parameters, ensuring proper context management when saving tasks.json. - This change aligns with recent enhancements in task management, preventing potential data corruption and improving overall reliability. * feat(fix-dependencies): Add projectRoot and tag parameters for enhanced context management - Updated `fixDependenciesDirect` and `registerFixDependenciesTool` to include `projectRoot` and `tag` parameters, improving context handling during dependency fixes. - Introduced a new unit test for `fixDependenciesCommand` to ensure proper preservation of projectRoot and tag data in JSON outputs. This change enhances the reliability of dependency management by ensuring that context is maintained across operations, preventing potential data issues. * fix(context): propagate projectRoot and tag through dependency, expansion, status-update and tag-management commands to prevent cross-tag data corruption * test(fix-dependencies): Enhance unit tests for fixDependenciesCommand - Refactored tests to use unstable mocks for utils, ui, and task-manager modules, improving isolation and reliability. - Added checks for process.exit to ensure proper handling of invalid data scenarios. - Updated test cases to verify writeJSON calls with projectRoot and tag parameters, ensuring accurate context preservation during dependency fixes. This change strengthens the test suite for dependency management, ensuring robust functionality and preventing potential data issues. * chore(plan): remove outdated fix plan for `writeJSON` context parameters
Task Master 
By @eyaltoledano, @RalphEcom & @jasonzhou1993
A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.
Documentation
For more detailed information, check out the documentation in the docs directory:
- Configuration Guide - Set up environment variables and customize Task Master
- Tutorial - Step-by-step guide to getting started with Task Master
- Command Reference - Complete list of all available commands
- Task Structure - Understanding the task format and features
- Example Interactions - Common Cursor AI interaction examples
- Migration Guide - Guide to migrating to the new project structure
Quick Install for Cursor 1.0+ (One-Click)
📋 Click the copy button (top-right of code block) then paste into your browser:
cursor://anysphere.cursor-deeplink/mcp/install?name=taskmaster-ai&config=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
Note: After clicking the link, you'll still need to add your API keys to the configuration. The link installs the MCP server with placeholder keys that you'll need to replace with your actual API keys.
Requirements
Taskmaster utilizes AI across several commands, and those require a separate API key. You can use a variety of models from different AI providers provided you add your API keys. For example, if you want to use Claude 3.7, you'll need an Anthropic API key.
You can define 3 types of models to be used: the main model, the research model, and the fallback model (in case either the main or research fail). Whatever model you use, its provider API key must be present in either mcp.json or .env.
At least one (1) of the following is required:
- Anthropic API key (Claude API)
- OpenAI API key
- Google Gemini API key
- Perplexity API key (for research model)
- xAI API Key (for research or main model)
- OpenRouter API Key (for research or main model)
- Claude Code (no API key required - requires Claude Code CLI)
Using the research model is optional but highly recommended. You will need at least ONE API key (unless using Claude Code). Adding all API keys enables you to seamlessly switch between model providers at will.
Quick Start
Option 1: MCP (Recommended)
MCP (Model Control Protocol) lets you run Task Master directly from your editor.
1. Add your MCP config at the following path depending on your editor
| Editor | Scope | Linux/macOS Path | Windows Path | Key |
|---|---|---|---|---|
| Cursor | Global | ~/.cursor/mcp.json |
%USERPROFILE%\.cursor\mcp.json |
mcpServers |
| Project | <project_folder>/.cursor/mcp.json |
<project_folder>\.cursor\mcp.json |
mcpServers |
|
| Windsurf | Global | ~/.codeium/windsurf/mcp_config.json |
%USERPROFILE%\.codeium\windsurf\mcp_config.json |
mcpServers |
| VS Code | Project | <project_folder>/.vscode/mcp.json |
<project_folder>\.vscode\mcp.json |
servers |
Manual Configuration
Cursor & Windsurf (mcpServers)
{
"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"
}
}
}
}
🔑 Replace
YOUR_…_KEY_HEREwith your real API keys. You can remove keys you don't use.
Note
: If you see
0 tools enabledin the MCP settings, try removing the--package=task-master-aiflag fromargs.
VS Code (servers + type)
{
"servers": {
"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"
},
"type": "stdio"
}
}
}
🔑 Replace
YOUR_…_KEY_HEREwith your real API keys. You can remove keys you don't use.
2. (Cursor-only) Enable Taskmaster MCP
Open Cursor Settings (Ctrl+Shift+J) ➡ Click on MCP tab on the left ➡ Enable task-master-ai with the toggle
3. (Optional) Configure the models you want to use
In your editor's AI chat pane, say:
Change the main, research and fallback models to <model_name>, <model_name> and <model_name> respectively.
For example, to use Claude Code (no API key required):
Change the main model to claude-code/sonnet
Table of available models | Claude Code setup
4. Initialize Task Master
In your editor's AI chat pane, say:
Initialize taskmaster-ai in my project
5. Make sure you have a PRD (Recommended)
For new projects: Create your PRD at .taskmaster/docs/prd.txt
For existing projects: You can use scripts/prd.txt or migrate with task-master migrate
An example PRD template is available after initialization in .taskmaster/templates/example_prd.txt.
Note
While a PRD is recommended for complex projects, you can always create individual tasks by asking "Can you help me implement [description of what you want to do]?" in chat.
Always start with a detailed PRD.
The more detailed your PRD, the better the generated tasks will be.
6. Common Commands
Use your AI assistant to:
- 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
More examples on how to use Task Master in chat
Option 2: Using Command Line
Installation
# Install globally
npm install -g task-master-ai
# OR install locally within your project
npm install task-master-ai
Initialize a new project
# If installed globally
task-master init
# If installed locally
npx task-master init
# Initialize project with specific rules
task-master init --rules cursor,windsurf,vscode
This will prompt you for project details and set up a new project with the necessary files and structure.
Common Commands
# Initialize a new project
task-master init
# 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 task(s) - supports comma-separated IDs
task-master show 1,3,5
# Research fresh information with project context
task-master research "What are the latest best practices for JWT authentication?"
# Generate task files
task-master generate
# Add rules after initialization
task-master rules add windsurf,roo,vscode
Claude Code Support
Task Master now supports Claude models through the Claude Code CLI, which requires no API key:
- Models:
claude-code/opusandclaude-code/sonnet - Requirements: Claude Code CLI installed
- Benefits: No API key needed, uses your local Claude instance
Learn more about Claude Code setup
Troubleshooting
If task-master init doesn't respond
Try running it with Node directly:
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
Contributors
Star History
Licensing
Task Master is licensed under the MIT License with Commons Clause. This means you can:
✅ Allowed:
- Use Task Master for any purpose (personal, commercial, academic)
- Modify the code
- Distribute copies
- Create and sell products built using Task Master
❌ Not Allowed:
- Sell Task Master itself
- Offer Task Master as a hosted service
- Create competing products based on Task Master
See the LICENSE file for the complete license text and licensing details for more information.