Cursor Task Master
An AI-powered task management system that works directly with Cursor IDE, using the built-in Cursor agent for task generation, analysis, and expansion.
Features
- Parse PRDs into structured tasks with dependencies
- Track task status (pending, in-progress, done)
- Break down complex tasks into subtasks
- Analyze task complexity
- Show the next task to work on based on dependencies
- Update future tasks based on implementation changes
- Generate detailed task files for better organization
- MCP integration for running tasks without confirmation
MCP Integration
Cursor Task Master can be integrated with MCP (Multi-Command Platform) to allow executing commands without requiring manual confirmation.
Using MCP Integration
- First, import and register the tools with MCP:
const { mcpIntegration } = require('cursor-task-master');
// Register the tools with MCP
mcpIntegration.registerMCPTools(cursorMCP);
- Then use the tools in your code:
// Load tasks without confirmation
const tasksData = await cursorMCP.executeTool('cursor_task_loadTasks', {});
// Get the next task to work on
const nextTask = await cursorMCP.executeTool('cursor_task_getNextTask', {
tasks: tasksData.tasks
});
// Update task status
await cursorMCP.executeTool('cursor_task_setTaskStatus', {
ids: [nextTask.id],
status: 'in-progress'
});
Installation
# Clone the repository
git clone https://github.com/tradesdontlie/cursor-task-master.git
# Install dependencies
cd cursor-task-master
npm install
# Make the CLI executable
npm link
License
MIT
Cursor Task Master
Project Details
- tradesdontlie/cursor-task-master
- Last Updated: 6/6/2025
Recomended MCP Servers
A Model Context Protocol Server for Pica
The API platform for mission-critical applications
DOC TALK - AI is an interactive application that allows users to chat with their documents using artificial...
Send emails directly from Cursor with this email sending MCP server
MCP server that provides tools and resources for integrating Hugeicons into various platforms. It implements a Model Context...
Lightweight PDF Q&A tool powered by RAG (Retrieval-Augmented Generation) with MCP (Model Context Protocol) Support.
android图片识别、android语音识别、android垃圾分类
PromptLab transforms basic user queries into optimized prompts for AI systems --> Built using MCP
A MCP server for Claude Desktop that enables Perplexity.ai searching
Model Context Protocol (MCP) Server for EigenLayer
This read-only MCP Server allows you to connect to GitHub data from Claude Desktop through CData JDBC Drivers....





