MCP Node.js TypeScript API

MCP Node.js TypeScript API

Exposes a Node.js REST API for user and product management through MCP tools, allowing AI assistants to directly interact with MongoDB to create, read, update, and delete users and products.

Category
访问服务器

README

MCP Node.js TypeScript API

A Node.js REST API built with TypeScript, TypeORM, MongoDB, and OpenAPI following a layered architecture with feature-based organization.

🏗️ Architecture

This project follows a layered architecture organized by features:

src/
├── config/              # Configuration files
│   ├── database.ts      # Database configuration
│   └── swagger.ts       # OpenAPI/Swagger configuration
├── features/            # Feature modules
│   ├── user/
│   │   ├── entities/    # TypeORM entities
│   │   ├── dtos/        # Data Transfer Objects
│   │   ├── repositories/# Data access layer
│   │   ├── services/    # Business logic layer
│   │   ├── controllers/ # HTTP request handlers
│   │   └── routes/      # Route definitions
│   └── product/
│       ├── entities/
│       ├── dtos/
│       ├── repositories/
│       ├── services/
│       ├── controllers/
│       └── routes/
├── middleware/          # Express middlewares
├── app.ts              # Express app setup
└── index.ts            # Application entry point

✨ Features

User Feature

  • Attributes: email, password (hashed), pictureUrl, name
  • Endpoints:
    • POST /api/users - Create a new user
    • GET /api/users - Get all users
    • GET /api/users/:id - Get user by ID
    • PUT /api/users/:id - Update user
    • DELETE /api/users/:id - Delete user

Product Feature

  • Attributes: name, description, pictureUrl, unitPrice, quantity, measureType, attributes (map)
  • Endpoints:
    • POST /api/products - Create a new product
    • GET /api/products - Get all products
    • GET /api/products/:id - Get product by ID
    • PUT /api/products/:id - Update product
    • DELETE /api/products/:id - Delete product

🤖 MCP (Model Context Protocol) Integration

This project includes an MCP server that exposes all API endpoints as MCP tools, allowing AI assistants like Claude to interact with your API directly.

MCP Tools Available

User Management Tools:

  • create_user - Create a new user
  • get_all_users - Retrieve all users
  • get_user_by_id - Get a specific user by ID
  • update_user - Update an existing user
  • delete_user - Delete a user

Product Management Tools:

  • create_product - Create a new product
  • get_all_products - Retrieve all products
  • get_product_by_id - Get a specific product by ID
  • update_product - Update an existing product
  • delete_product - Delete a product

Running the MCP Server

  1. Build the project:

    npm run build
    
  2. Run the MCP server:

    npm run mcp
    

    Or for development:

    npm run mcp
    

Configuring Claude Desktop

To use this MCP server with Claude Desktop, add the configuration to your Claude Desktop config file:

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Add this configuration (adjust the path to match your installation):

{
  "mcpServers": {
    "mcpnodefil": {
      "command": "node",
      "args": [
        "c:/Users/USER/Desktop/aimcpproj/mcpnodefil/dist/mcp/index.js"
      ],
      "env": {
        "MONGODB_URI": "mongodb://localhost:27017/mcpnodefil",
        "PORT": "3000"
      }
    }
  }
}

Important: Make sure MongoDB is running before starting the MCP server, as it connects to the database on startup.

MCP Server Features

  • Direct Database Access: The MCP server connects directly to MongoDB, bypassing the REST API
  • Type Safety: All tools use TypeScript for type safety
  • Validation: Input validation using class-validator DTOs
  • Error Handling: Comprehensive error handling with detailed error messages
  • Automatic Shutdown: Graceful shutdown on SIGINT/SIGTERM signals

🚀 Getting Started

Prerequisites

  • Node.js (v16 or higher)
  • MongoDB (running locally or remote instance)
  • npm or yarn

Installation

  1. Clone the repository

    git clone <repository-url>
    cd mcpnodefil
    
  2. Install dependencies

    npm install
    
  3. Configure environment variables

    cp .env.example .env
    

    Edit .env file with your configuration:

    PORT=3000
    NODE_ENV=development
    MONGODB_URI=mongodb://localhost:27017/mcpnodefil
    
  4. Start MongoDB Make sure MongoDB is running on your system:

    # If using local MongoDB
    mongod
    
    # Or using Docker
    docker run -d -p 27017:27017 --name mongodb mongo:latest
    
  5. Run the application

    Development mode (with auto-reload):

    npm run dev
    

    Build for production:

    npm run build
    

    Run production build:

    npm start
    

📚 API Documentation

Once the server is running, you can access:

🧪 Testing the API

Using cURL

Create a user:

curl -X POST http://localhost:3000/api/users \
  -H "Content-Type: application/json" \
  -d '{
    "email": "user@example.com",
    "password": "password123",
    "name": "John Doe",
    "pictureUrl": "https://example.com/photo.jpg"
  }'

Create a product:

curl -X POST http://localhost:3000/api/products \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Product Name",
    "description": "Product Description",
    "pictureUrl": "https://example.com/product.jpg",
    "unitPrice": 29.99,
    "quantity": 100,
    "measureType": "unit",
    "attributes": {
      "color": "blue",
      "size": "medium"
    }
  }'

Get all users:

curl http://localhost:3000/api/users

Get all products:

curl http://localhost:3000/api/products

🛠️ Technology Stack

  • Runtime: Node.js
  • Language: TypeScript
  • Framework: Express.js
  • Database: MongoDB
  • ORM: TypeORM
  • Validation: class-validator
  • Documentation: Swagger/OpenAPI
  • Security: bcrypt (password hashing)

📁 Project Structure Details

Layers

  1. Entities Layer: TypeORM entities that map to MongoDB collections
  2. DTOs Layer: Data Transfer Objects for request/response validation
  3. Repository Layer: Data access and database operations
  4. Service Layer: Business logic and orchestration
  5. Controller Layer: HTTP request handling and response formatting
  6. Routes Layer: API endpoint definitions

Key Design Patterns

  • Dependency Injection: Manual DI through constructors
  • Repository Pattern: Abstraction of data access logic
  • Service Pattern: Business logic separation
  • DTO Pattern: Request/response validation and transformation

🔒 Security Features

  • Password hashing with bcrypt (10 salt rounds)
  • Input validation using class-validator
  • CORS enabled for cross-origin requests
  • Environment variable configuration

📝 Scripts

  • npm run dev - Start development server with hot reload
  • npm run build - Compile TypeScript to JavaScript
  • npm start - Run compiled JavaScript in production mode
  • npm run mcp - Run MCP server (development mode)
  • npm run mcp:build - Build and run MCP server (production mode)
  • npm run typeorm - Run TypeORM CLI commands

🤝 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.

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