Task Master

Task Master

Simplified Trello-style task management via MCP with 11 essential tools for efficient CRUD operations and a real-time web dashboard.

Category
访问服务器

README

Task Master

🎯 Simplified Trello-style task management for MCP - Pure MCP functionality with 11 essential tools for efficient CRUD task management, eliminating complex LLM-dependent features.

<div align="center">

Version License: MIT TypeScript

Quick StartDocumentationMCP Tools

</div>

🚀 Quick Start

Prerequisites

  • Node.js 18+
  • An MCP client (Claude Desktop, VSCode with MCP extension, etc.)

Installation

  1. Clone and build

    git clone https://github.com/yourusername/mcp-task-master
    cd mcp-task-master
    npm install && npm run build
    
  2. Configure MCP client

    Add to your MCP client configuration (e.g., ~/.claude/config.json):

    {
      "mcpServers": {
        "task-master": {
          "command": "node",
          "args": ["/path/to/mcp-task-master/dist/index.js"],
          "env": {
            "DATA_DIR": "/path/to/your/task/data"
          }
        }
      }
    }
    
  3. Start using

    # List all tasks
    list_tasks --status all
    
    # Create a task (via Dashboard)
    start_dashboard
    

✨ Key Features

  • 🎯 Simplified: Reduced from 19 to 11 essential MCP tools (42% reduction)
  • ⚡ Pure MCP: No complex LLM dependencies, focusing on true MCP efficiency
  • 🌐 Bilingual: Korean/English support
  • 📊 Dashboard: Real-time React-based web interface
  • 🔄 Trello-style: Intuitive CRUD task management

🛠 MCP Tools (11 Essential Tools)

💼 Core Task Management (7 tools)

  • list_tasks - List all tasks by status with Trello-style emojis
  • execute_task - Simplified task execution guide
  • get_task_detail - View complete task information
  • query_task - Search tasks by keywords or ID
  • update_task - Modify task content and properties
  • delete_task - Remove specific tasks
  • clear_all_tasks - Clear all tasks with backup

📊 Dashboard Management (4 tools)

  • start_dashboard - Launch React web interface
  • stop_dashboard - Stop dashboard server
  • status_dashboard - Check server status
  • list_dashboard_projects - View registered projects
  • add_dashboard_project - Register new projects
  • create_tasks_in_project - Create project-specific tasks

📚 Documentation

Task Data Model (Simplified)

interface Task {
  id: string;                    // UUID
  name: string;                  // Task name
  description: string;           // Task description
  notes?: string;               // Additional notes
  status: TaskStatus;           // pending | in_progress | completed | blocked
  dependencies: TaskDependency[]; // Task dependencies
  createdAt: Date;              // Creation date
  updatedAt: Date;              // Last modified
  completedAt?: Date;           // Completion date
  summary?: string;             // Completion summary
  relatedFiles?: RelatedFile[]; // Related files
  agent?: string;              // Assigned agent
}

Environment Variables

# Required
DATA_DIR="/path/to/task/data"

# Optional
LANG="ko"                    # Language (ko/en)
ENABLE_GUI="false"          # Enable web dashboard
WEB_PORT="3000"            # Dashboard port

🎮 Usage Examples

Basic Task Management

# List all tasks
list_tasks --status all

# Search tasks
query_task --query "fix bug" --page 1

# Get task details
get_task_detail --taskId "your-task-id"

# Update task
update_task --taskId "your-task-id" --name "New Task Name"

Dashboard Operations

# Start web dashboard
start_dashboard --port 9998

# Check dashboard status
status_dashboard

# Create project tasks
create_tasks_in_project --projectName "MyProject" --tasks '[{"title":"Task 1", "priority":"High"}]'

🏗 Architecture

src/
├── index.ts                 # MCP server entry point (11 tools)
├── models/taskModel.ts      # Simplified data models & CRUD
├── messages/                # Bilingual message system
│   ├── korean.ts           # Korean messages
│   └── english.ts          # English messages
├── tools/
│   ├── task/              # 7 core task tools
│   └── dashboard/         # 4 dashboard tools
├── types/index.ts          # Simplified type definitions
└── utils/                  # Common utilities

🚀 Performance Improvements

Metric Before After Improvement
MCP Tools 19 11 42% reduction
Code Size Complex ~49KB removed Significant
Template Files 140+ Direct messages Streamlined
Language Support 3 languages 2 languages Focused
Memory Usage High Reduced LLM system removed

⚡ What Was Removed

Complex LLM-dependent features:

  • plan_task - Complex task planning
  • analyze_task - Codebase analysis
  • split_tasks - Task decomposition (large files)
  • verify_task - Complex quality verification
  • reflect_task - Task retrospection
  • process_thought - Thought processing
  • research_mode - Research mode
  • init_project_rules - Project rules initialization

Simplified data model:

  • implementationGuide - Complex implementation guides
  • verificationCriteria - Quality verification criteria
  • analysisResult - LLM-based analysis results
  • ❌ Complex template system (140+ files)

🤝 Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

  • Built for the Model Context Protocol (MCP)
  • Inspired by Trello's simplicity and effectiveness
  • Focused on pure MCP efficiency without LLM complexity

<div align="center">

Task Master - Simplified. Efficient. Pure MCP.

⭐ Star this repo if you find it useful!

</div>

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