YApi MCP Enhanced

<div align="center">

An enhanced Model Context Protocol (MCP) server for YApi that enables seamless AI integration

English | 简体中文

Empower Claude, Cursor, and other AI tools with intelligent YApi API management capabilities

🚀 Quick Start • 🔧 Installation • 💻 Platforms • 📖 Documentation • 🤝 Contributing

</div>

🌟 Features

🚀 Quick Start

Prerequisites

• Node.js 18+
• YApi Server with API access
• YApi Project Token

⚡ One-line Installation

# Install globally
npm install -g @kedoupi/yapi-mcp

# Test your connection
npx @kedoupi/yapi-mcp test-connection

🔧 Installation

<details> <summary>📦 NPM Installation</summary>

npm install -g @kedoupi/yapi-mcp

</details>

<details> <summary>🧶 Yarn Installation</summary>

yarn global add @kedoupi/yapi-mcp

</details>

<details> <summary>🔨 Development Installation</summary>

git clone https://github.com/kedoupi/yapi-mcp.git
cd yapi-mcp
npm install
npm run build

</details>

⚙️ Configuration

1. Copy environment template:

cp .env.example .env

1. Configure your YApi settings:

# Required
YAPI_BASE_URL=https://your-yapi-domain.com
YAPI_PROJECT_TOKEN=your-project-token

# Optional  
LOG_LEVEL=info
CACHE_TTL=300

1. Test connection:

npx @kedoupi/yapi-mcp test-connection

💻 Platform Integration

🤖 Claude Desktop

<details> <summary>Configure Claude Desktop</summary>

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "@kedoupi/yapi-mcp": {
      "command": "npx",
      "args": ["@kedoupi/yapi-mcp"],
      "env": {
        "YAPI_BASE_URL": "https://your-yapi-domain.com",
        "YAPI_PROJECT_TOKEN": "your-project-token",
        "LOG_LEVEL": "info"
      }
    }
  }
}

Config file locations:

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

</details>

🎯 Cursor IDE

<details> <summary>Configure Cursor</summary>

1. Open Cursor Settings (Cmd/Ctrl + ,)
2. Search for "MCP" or go to Extensions > MCP
3. Add new MCP server:

{
  "name": "@kedoupi/yapi-mcp", 
  "command": "npx",
  "args": ["@kedoupi/yapi-mcp"],
  "env": {
    "YAPI_BASE_URL": "https://your-yapi-domain.com",
    "YAPI_PROJECT_TOKEN": "your-project-token"
  }
}

</details>

🔄 Continue (VS Code)

<details> <summary>Configure Continue</summary>

Add to .continue/config.json:

{
  "mcpServers": [
    {
      "name": "@kedoupi/yapi-mcp",
      "command": "npx", 
      "args": ["@kedoupi/yapi-mcp"],
      "env": {
        "YAPI_BASE_URL": "https://your-yapi-domain.com",
        "YAPI_PROJECT_TOKEN": "your-project-token"
      }
    }
  ]
}

</details>

🧠 Codeium

<details> <summary>Configure Codeium</summary>

Add MCP server configuration in Codeium settings:

{
  "mcp_servers": {
    "yapi": {
      "command": "npx",
      "args": ["@kedoupi/yapi-mcp"], 
      "env": {
        "YAPI_BASE_URL": "https://your-yapi-domain.com",
        "YAPI_PROJECT_TOKEN": "your-project-token"
      }
    }
  }
}

</details>

🔗 Other Platforms

The server supports any MCP-compatible AI tool. Check our integration guide for more platforms.

🛠️ Available Tools

The server provides these tools for AI interaction:

<details> <summary>🔍 Tool Details</summary>

yapi_search_interfaces

Advanced search with multiple filters:

• project_id (optional): Filter by project
• catid (optional): Filter by category
• q (optional): Search query string
• page (optional): Page number for pagination
• limit (optional): Results per page (max 100)

yapi_create_interface / yapi_update_interface

Full interface management with support for:

• Request/response body specifications
• Headers and query parameters
• HTTP methods (GET, POST, PUT, DELETE, etc.)
• Interface status and descriptions
• Category assignments

</details>

🏗️ Architecture

graph TD
    A[AI Tool] -->|MCP Protocol| B[YApi MCP Server]
    B -->|HTTP API| C[YApi Server]
    B -->|Cache| D[Memory Cache]
    B -->|Logging| E[Logger]
    B -->|Config| F[Environment]

• YApiClient: HTTP client for YApi API interactions
• MCP Server: Protocol handler for AI tool integration
• Caching: Intelligent caching for performance optimization
• Configuration: Environment-based configuration management
• Error Handling: Comprehensive error management

🧪 Development

Local Development

# Clone repository
git clone https://github.com/kedoupi/yapi-mcp.git
cd yapi-mcp

# Install dependencies
npm install

# Development mode (watch files)
npm run dev

# Build project
npm run build

# Start server
npm start

Testing

# Run all tests
npm test

# Watch mode
npm run test:watch

# Coverage report
npm run test:coverage

# Unit tests only
npm run test:unit

# Integration tests
npm run test:integration

Code Quality

# Lint code
npm run lint

# Fix issues
npm run lint:fix

# Clean build
npm run clean

📊 Performance

• ⚡ Fast Response: < 100ms for cached requests
• 💾 Memory Efficient: < 50MB RAM usage
• 🔄 Smart Caching: 5-minute TTL with cleanup
• 📈 Scalable: Handles 1000+ concurrent requests

🤝 Contributing

We welcome all contributions! Here's how you can help:

🐛 Bug Reports

Found a bug? Open an issue

💡 Feature Requests

Have an idea? Request a feature

🔧 Code Contributions

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

See our Contributing Guide for detailed information.

🌟 Other Ways to Help

• ⭐ Star the repository
• 📢 Share with others
• 📝 Improve documentation
• 🧪 Test new features

📋 Roadmap

🎯 Current Focus

• [ ] Enhanced Mock data support
• [ ] Batch operations for multiple APIs
• [ ] Real-time synchronization with YApi
• [ ] Multi-project parallel management

🔮 Future Plans

• [ ] GraphQL API support
• [ ] Web-based configuration UI
• [ ] Custom plugin system
• [ ] Advanced analytics dashboard
• [ ] Docker container support

🏆 Comparison

🔗 Related Projects

• [YApi](https://github.com/YMFE/yapi) - Visual API management platform
• [Model Context Protocol](https://github.com/modelcontextprotocol) - AI tool communication standard
• [Claude Desktop](https://claude.ai/download) - Anthropic's desktop application
• [Cursor](https://cursor.sh/) - AI-powered code editor

📄 License

This project is licensed under the MIT License.

🆘 Support

Need help? We're here for you:

• 📖 Documentation
• 🐛 Report Issues
• 💬 Discussions
• 📧 Email Support

🙏 Acknowledgments

Special thanks to:

• YApi Team for the excellent API management platform
• Anthropic for the Model Context Protocol
• All Contributors who make this project better
• Open Source Community for inspiration and support

<div align="center">

If this project helps you, please give us a ⭐️

Made with ❤️ by kedoupi and contributors

🏠 Homepage • 📚 Docs • 🐛 Issues • 💬 Discussions

</div>