What is Openapi2mcp

OpenAPI2MCP is a Python tool that serves as a Model Context Protocol (MCP) server, enabling interaction between LLMs and AI applications with APIs defined by OpenAPI specifications (JSON or YAML).

Use cases

Use cases for OpenAPI2MCP include creating interactive AI applications, integrating with existing APIs, and enabling real-time data communication in applications.

How to use

To use OpenAPI2MCP, install it via pip, convert an OpenAPI spec file to MCP tools using the command ‘openapi2mcp convert’, and start the MCP server with ‘openapi2mcp serve’.

Key features

Key features include converting OpenAPI specifications to MCP tools, serving MCP endpoints, OAuth authentication support, Server-Sent Events (SSE) for real-time communication, a command-line interface, and a programmatic API for integration.

Where to use

OpenAPI2MCP can be used in various fields such as software development, AI applications, and any environment where APIs are defined using OpenAPI specifications.

OpenAPI2MCP

OpenAPI2MCP is a Python tool that serves as a Model Context Protocol (MCP) server with tools generated from OpenAPI specification files (JSON or YAML). It allows LLMs and AI applications that support MCP to interact with any API that has an OpenAPI specification.

Features

• 🔄 Convert OpenAPI specifications to MCP tools
• 🛠️ Serve MCP endpoints with tools from OpenAPI specs
• 🔐 OAuth authentication support for API calls
• 📡 Server-Sent Events (SSE) support for real-time communication
• 💻 Command-line interface for easy usage
• 🧩 Programmatic API for integration into other applications

Installation

pip install openapi2mcp

Quick Start

Convert an OpenAPI spec to MCP tools:

openapi2mcp convert --spec-file openapi.yaml --output tools.json

Start an MCP server with tools from an OpenAPI spec:

openapi2mcp serve --spec-file openapi.yaml --port 8000

Use environment variables for OAuth authentication:

API_CLIENT_ID=your_client_id
API_CLIENT_SECRET=your_client_secret
API_TOKEN_URL=https://example.com/oauth/token

Documentation

• Getting Started
• Usage Documentation
• Architecture
• GitHub API Example

Examples

The examples directory contains sample code to help you get started:

• Sample API specification
• Basic server example
• Client example
• Advanced usage

How It Works

OpenAPI2MCP bridges the gap between APIs defined with OpenAPI specifications and AI systems that support the Model Context Protocol (MCP):

1. It parses OpenAPI specifications to extract API endpoints
2. Converts these endpoints into MCP tools with appropriate parameters
3. Creates an MCP server that exposes these tools
4. Handles authentication with the API
5. Executes tool calls by making appropriate API requests

This allows AI models and applications to interact with any API through the standardized MCP interface.

+---------------------+     +---------------------+     +---------------------+
|                     |     |                     |     |                     |
|   OpenAPI Spec      |     |   OpenAPI2MCP       |     |   MCP-Compatible    |
|   (JSON/YAML)       +---->+   Server            +---->+   LLM/Client        |
|                     |     |                     |     |                     |
+---------------------+     +---------------------+     +---------------------+
                             |        ^
                             |        |
                             v        |
+---------------------+     +---------------------+
|                     |     |                     |
|   OAuth             |     |   API Endpoint      |
|   Authentication    +---->+   (e.g. GitHub API) |
|                     |     |                     |
+---------------------+     +---------------------+

Why Use OpenAPI2MCP?

• Universal API Access: Connect any OpenAPI-defined API to MCP-compatible LLMs
• Tool Discovery: LLMs can dynamically discover what capabilities are available
• Authentication Handling: Securely manage API credentials
• Standard Interface: Consistent way to interact with diverse APIs
• Easy Integration: Simple setup process for both local and production use

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Install development dependencies (pip install -e ".[dev]")
4. Make your changes
5. Run tests (pytest)
6. Commit your changes (git commit -m 'Add some amazing feature')
7. Push to the branch (git push origin feature/amazing-feature)
8. Open a Pull Request

License

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