MCPHy
Transform REST APIs into intelligent, chat-driven MCP servers with zero code changes. Simply point it at your Swagger/OpenAPI specification to get natural language querying capabilities powered by AI.
README
<div align="center">
███╗ ███╗ ██████╗██████╗ ██╗ ██╗██╗ ██╗
████╗ ████║██╔════╝██╔══██╗██║ ██║╚██╗ ██╔╝
██╔████╔██║██║ ██████╔╝███████║ ╚████╔╝
██║╚██╔╝██║██║ ██╔═══╝ ██╔══██║ ╚██╔╝
██║ ╚═╝ ██║╚██████╗██║ ██║ ██║ ██║
╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═╝ ╚═╝ ╚═╝
🚀 Turn Any API into a Conversational AI Powerhouse
Transform your REST APIs into intelligent, chat-driven MCP servers with zero code changes
🚀 Ready to try? npm install -g mcphy • 🎯 Quick Start • 📖 API Docs • 🎨 Examples • ⭐ Star
</div>
Requirements
- Node.js >= 18.0.0
- npm >= 9.0.0
- An API specification file (Swagger/OpenAPI)
Installation
# Option 1: Install globally
npm install -g mcphy
# Option 2: Try without installing
npx mcphy --help
Quick Start
# 1. Initialize with your API spec
mcphy init
# 2. Start the conversational server
mcphy serve
# 3. Open your browser
open http://localhost:3000
That's it! Start chatting with your API in plain English.
Try It Now
Want to test MCPhy immediately? Use our included example:
# Clone and test with example API
git clone https://github.com/sehmim/mcphy.git
cd mcphy
npm install
npm run build
npm link
# Test with example
cd examples
mcphy init -f sample-swagger.yaml
mcphy serve
Then open http://localhost:3000 and try:
- "Show me all pets"
- "Create a new pet named Max"
- "Get pet with ID 1"
What It Does
- 🧠 Natural Language Processing - Ask questions in plain English
- 🔌 Real API Calls - Actually makes requests to your backend
- ⚠️ Smart Guidance - Helps when information is missing
- 💬 Web Interface - Beautiful chat UI with real-time responses
- 📦 Export Ready - Create standalone packages
Example
You: "create booking for John Doe for oil change for 2025-01-15"
MCPhy: ✅ Matched POST /bookings
📤 Making API call...
📋 Response: {"id": "booking-123", "status": "created"}
Why Developers Love This
- Zero Code Changes - Works with existing APIs
- Natural Language - No need to remember endpoint names
- Real Responses - Actually calls your backend
- Smart Guidance - Helps when information is missing
- Beautiful UI - Professional chat interface
- Easy Export - Create standalone packages
Commands
| Command | Description |
|---|---|
mcphy init |
Initialize project with API spec |
mcphy serve |
Start the MCP server |
mcphy validate <file> |
Validate API specification |
mcphy export |
Create standalone package |
Supported Formats
- ✅ OpenAPI 3.0+
- ✅ Swagger 2.0
- ⏳ Postman Collections (coming soon)
Documentation
- 📖 API Reference - Programmatic usage
- 🎨 Examples - Real-world examples
Development
git clone https://github.com/sehmim/mcphy.git
cd mcphy
npm install
npm run build
npm link
License
MIT © 2025 MCPhy
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
<div align="center">
Made with ❤️ by developers, for developers
</div>
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。