RTaskmaster MCP

RTaskmaster MCP

A task management MCP server for AI-driven development, enabling creation, tracking, and organization of tasks with subtasks, priorities, and dependencies via natural language commands.

Category
访问服务器

README

RTaskmaster MCP

A task master MCP (Model Context Protocol) server for AI-driven development in VS Code, Cursor, and other MCP-compatible editors.

npm version

Features

  • 📋 Task Management: Create, update, list, and organize tasks
  • 🎯 Subtasks: Break down complex tasks into manageable subtasks
  • 📊 Status Tracking: Track progress with status updates (pending, in-progress, done, blocked, deferred)
  • 🏷️ Priority Levels: Organize by priority (high, medium, low)
  • 🔗 Dependencies: Define task dependencies
  • 💾 JSON Storage: Simple file-based storage in .rtaskmaster/tasks.json
  • 🤖 AI-Ready: Designed to work seamlessly with GitHub Copilot, Claude, and other AI assistants

Quick Install for VS Code

Option 1: NPX (Recommended - No Install Required)

Add to your VS Code MCP configuration at .vscode/mcp.json in your project:

{
  "servers": {
    "rtaskmaster": {
      "command": "npx",
      "args": ["-y", "rtaskmaster-mcp"],
      "type": "stdio"
    }
  }
}

Option 2: Global Install

npm install -g rtaskmaster-mcp

Then add to .vscode/mcp.json:

{
  "servers": {
    "rtaskmaster": {
      "command": "rtaskmaster-mcp",
      "type": "stdio"
    }
  }
}

Option 3: Cursor IDE

Add to ~/.cursor/mcp.json or your project's .cursor/mcp.json:

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

📖 AI Agent Instructions

For AI agents (GitHub Copilot, Claude, etc.) to work effectively with RTaskmaster, reference the instructions file:

Location: .github/instructions.md in this repository

The instructions file provides:

  • ✅ Getting started workflow
  • ✅ Task lifecycle management
  • ✅ Best practices for AI agents
  • ✅ TASKS.md checklist format
  • ✅ Example sessions

Quick Workflow for AI Agents

  1. Initialize: rtaskmaster_init at project start
  2. Create tasks: Break down requirements into tasks
  3. Generate checklist: rtaskmaster_generate_tasks_md for human-readable view
  4. Work loop: rtaskmaster_next_task → work → rtaskmaster_set_status → repeat
  5. Track progress: rtaskmaster_stats to see completion

Available MCP Tools

Tool Description
rtaskmaster_init Initialize RTaskmaster in a project
rtaskmaster_get_tasks Get all tasks with optional filtering
rtaskmaster_get_task Get a specific task by ID
rtaskmaster_create_task Create a new task
rtaskmaster_update_task Update an existing task
rtaskmaster_delete_task Delete a task
rtaskmaster_set_status Update task status
rtaskmaster_add_subtask Add a subtask to a task
rtaskmaster_next_task Get the next task to work on
rtaskmaster_stats Get project statistics
rtaskmaster_generate_tasks_md Generate a human-readable TASKS.md checklist
rtaskmaster_parse_prd Parse requirements/PRD files to create tasks
rtaskmaster_bulk_status Update multiple task statuses at once

📋 TASKS.md Checklist File

RTaskmaster can generate a human-readable TASKS.md file that serves as a visual checklist:

# Project Tasks

## 📊 Progress

| Status         | Count |
| -------------- | ----- |
| ✅ Done        | 2     |
| 🔄 In Progress | 1     |
| ⏳ Pending     | 3     |
| **Total**      | **6** |

**Completion: 33%**

---

## ✅ Tasks

### 🔴 High Priority

- [x] Set up project structure (#1)
- [ ] 🔄 Implement authentication (#2)
  - [x] Set up OAuth (#2.1)
  - [ ] Add JWT tokens (#2.2)

### 🟡 Medium Priority

- [ ] Add user profile page (#3)

Generate this file anytime using rtaskmaster_generate_tasks_md.

Task Structure

Tasks are stored in .rtaskmaster/tasks.json:

{
  "version": "1.0.0",
  "projectName": "My Project",
  "tasks": [
    {
      "id": "1",
      "title": "Implement authentication",
      "description": "Add user authentication system",
      "status": "pending",
      "priority": "high",
      "dependencies": [],
      "subtasks": [
        {
          "id": "1",
          "title": "Set up OAuth",
          "status": "pending"
        }
      ],
      "details": "Implementation notes here...",
      "testStrategy": "How to verify this task...",
      "createdAt": "2026-01-13T10:00:00.000Z",
      "updatedAt": "2026-01-13T10:00:00.000Z"
    }
  ],
  "lastUpdated": "2026-01-13T10:00:00.000Z"
}

Usage Examples

Once configured, interact through your AI assistant:

Initialize taskmaster in this project

Create a task to implement user authentication with high priority

Show me all pending tasks

What's the next task I should work on?

Mark task 1 as in-progress

Add a subtask to task 1: "Set up database schema"

Task Statuses

Status Description
pending Task not yet started
in-progress Currently being worked on
done Completed
blocked Cannot proceed (waiting on something)
deferred Postponed for later

Priority Levels

Priority Description
high Urgent/critical tasks
medium Normal priority (default)
low Can wait

Development

# Clone the repo
git clone https://github.com/RagnarPitla/RTaskmaster-rbuildai-mcp.git
cd RTaskmaster-rbuildai-mcp

# Install dependencies
npm install

# Build
npm run build

# Watch mode for development
npm run dev

# Test with MCP Inspector
npm run inspector

Contributing

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

License

MIT

Author

RBuildAI - GitHub

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选