todo-mcp-server

todo-mcp-server

Enables Gemini CLI and other AI assistants to manage todos (create, read, update, delete, filter) through natural language commands via the Model Context Protocol.

Category
访问服务器

README

Todo List App with FastAPI and MCP Integration

A complete todo list application with a modern web interface, REST API built with FastAPI, and Model Context Protocol (MCP) integration for Gemini CLI.

Features

Backend API

  • Create, read, update, and delete todos
  • Mark todos as completed or pending
  • Filter todos by completion status
  • Automatic API documentation with Swagger UI
  • RESTful API endpoints

Frontend Interface

  • Modern, responsive web interface
  • Interactive todo management
  • Real-time statistics
  • Filter todos by status (All, Pending, Completed)
  • Edit and delete todos with confirmation
  • Beautiful gradient design with animations
  • Mobile-friendly responsive layout

MCP Integration

  • Model Context Protocol (MCP) server for AI assistant integration
  • Gemini CLI support - Control your todos through natural language
  • FastMCP framework for seamless AI integration
  • Complete tool set for todo management via AI
  • Natural language interface for todo operations

Setup

Basic Setup

  1. Activate the virtual environment:

    source venv/bin/activate
    
  2. Install dependencies:

    pip install -r requirements.txt
    
  3. Run the application:

    python main.py
    

    Or alternatively:

    uvicorn main:app --reload
    

MCP Integration Setup

For AI assistant integration with Gemini CLI:

  1. Start both services (FastAPI app + MCP server):

    ./start_services.sh
    
  2. Configure Gemini CLI by adding to your Gemini config:

    {
      "mcpServers": {
        "todo-mcp-server": {
          "command": "/path/to/your/project/venv/bin/python",
          "args": ["mcp_server.py"],
          "cwd": "/path/to/your/project"
        }
      }
    }
    
  3. Test with Gemini CLI:

    • "Show me all my todos"
    • "Create a new todo called 'Learn FastAPI'"
    • "Mark todo as complete"
    • "What's my completion rate?"

See MCP_INTEGRATION_GUIDE.md for detailed setup instructions.

API Endpoints

  • GET / - Welcome message
  • GET /todos - Get all todos
  • GET /todos/{todo_id} - Get a specific todo
  • POST /todos - Create a new todo
  • PUT /todos/{todo_id} - Update a todo
  • DELETE /todos/{todo_id} - Delete a todo
  • GET /todos/completed - Get completed todos
  • GET /todos/pending - Get pending todos

Access the Application

Once the server is running, visit:

  • Web Interface: http://localhost:8000 (Main todo list interface)
  • API Documentation: http://localhost:8000/docs (Swagger UI)
  • Alternative API Docs: http://localhost:8000/redoc

Example Usage

Create a new todo:

curl -X POST "http://localhost:8000/todos" \
     -H "Content-Type: application/json" \
     -d '{"title": "Learn FastAPI", "description": "Build a todo API", "completed": false}'

Get all todos:

curl -X GET "http://localhost:8000/todos"

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