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.
README
RTaskmaster MCP
A task master MCP (Model Context Protocol) server for AI-driven development in VS Code, Cursor, and other MCP-compatible editors.
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
- Initialize:
rtaskmaster_initat project start - Create tasks: Break down requirements into tasks
- Generate checklist:
rtaskmaster_generate_tasks_mdfor human-readable view - Work loop:
rtaskmaster_next_task→ work →rtaskmaster_set_status→ repeat - Track progress:
rtaskmaster_statsto 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
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。