A Python tool that automatically converts OpenAPI specifications into fully functional Model Context Protocol (MCP) servers. Generates Docker-ready implementations with support for SSE/IO communication protocols, authentication, and comprehensive error handling.
- 🔄 OpenAPI to MCP tools/resources conversion
 - 🐳 Docker-ready with multi-stage builds
 - 🔐 Multiple authentication methods
 - ⚡ Async operations & rate limiting
 - 📡 SSE/IO communication protocols
 - 📦 Modular code structure with package support
 
The generator has been refactored into a proper Python package while maintaining backward compatibility:
- Original Entry Point: The 
generator.pyscript still works exactly as before - Modular Organization: Code is now split into focused modules
 - Package Installation: Can be installed as a proper Python package
 - Same Templates: Uses the exact same templates in the 
/templatesdirectory - Docker Support: Preserves all Docker functionality
 
You can use the tool in whatever way you prefer:
- Run 
generator.pydirectly (original approach) - Install as a package and use 
mcp-generatorcommand - Use the module programmatically in your own Python code
 
For more details on the modular code structure, see MODULAR_REFACTORING.md.
- Convert OpenAPI specifications to MCP servers
 - Docker-ready implementation with multi-stage builds
 - Support for multiple authentication methods
 - Choice of SSE or IO communication protocols
 - Comprehensive error handling and logging
 - Built-in rate limiting and security features
 - Async operations for optimal performance
 - Extensive test suite with coverage reporting
 
- Python 3.10+
 - Docker (for running the generated server)
 - pip or uv (Python package manager)
 
# Clone the repository
git clone https://github.com/abutbul/openapi-mcp-generator.git
cd openapi-mcp-generator
# Install as a package (development mode)
pip install -e .
# Or using uv
uv venv
source .venv/bin/activate
uv pip install -e .pip install openapi-mcp-generator# Using the original script (still works the same way)
python generator.py openapi.yaml --output-dir ./output --api-url https://api.example.com
# Using the new modular CLI tool after installation
mcp-generator openapi.yaml --output-dir ./output --api-url https://api.example.com
# Using the python module directly
python -m openapi_mcp_generator.cli openapi.yaml --output-dir ./outputopenapi_file: Path to the OpenAPI YAML file (required)--output-dir: Output directory for the generated project (default: '.')--api-url: Base URL for the API--auth-type: Authentication type (bearer, token, basic)--api-token: API token for authentication--api-username: Username for basic authentication--api-password: Password for basic authentication
After generating the server, you can build and run it using Docker:
cd output/openapi-mcp-*
./docker.sh build
./docker.sh start --transport=sse --port=8000The generated docker.sh script supports the following commands:
build: Build the Docker imagestart: Start the container--port=PORT: Set the port (default: 8000)--transport=TYPE: Set transport type: 'sse' or 'io' (default: sse)--log-level=LEVEL: Set logging level (default: info)
stop: Stop the containerclean: Remove the container and imagelogs: View container logs
The modular generator has the following structure:
openapi-mcp-generator/
├── generator.py              # Original entry point (maintained for backward compatibility)
├── mcp_generator.py          # New entry point (uses the modular structure)
├── openapi_mcp_generator/    # Main package (new modular structure)
│   ├── __init__.py           # Package initialization
│   ├── cli.py                # Command-line interface
│   ├── generator.py          # Main generator module
│   ├── generators.py         # Code generators for tools/resources
│   ├── http.py               # HTTP client utilities
│   ├── parser.py             # OpenAPI parser
│   └── project.py            # Project builder
├── templates/                # Original templates directory (used by the modular code)
│   ├── config/
│   ├── docker/
│   ├── server/
│   ├── pyproject.toml
│   └── requirements.txt
├── samples/                  # Sample implementations
├── tests/                    # Test cases
├── LICENSE                   # License file
├── README.md                 # This file
├── pyproject.toml            # Project metadata
└── setup.py                  # Package setup
The modular structure preserves all the existing functionality while making the code more maintainable:
- The original entry point (
generator.py) can still be used as before - The existing templates in 
/templatesare used by the new modular code - All Docker-related functionality is preserved exactly as it was
 - The project can now be installed as a proper Python package
 
Check out our sample implementations to see the generator in action:
- Trilium Notes ETAPI Server - An MCP server for the Trilium Notes knowledge management system's ETAPI
 
- Fork the repository
 - Create a feature branch
 - Make your changes
 - Run the test suite
 - Submit a pull request
 
This project is licensed under the MIT License - see the LICENSE file for details.
To generate an MCP server from the Elasticsearch 6.1 spec folder:
# Run the original script directly
python generator.py samples/elasticsearch_6.1/api
# Or use the modular entry point
python mcp_generator.py samples/elasticsearch_6.1/apiFirst, install the package (from the project root):
pip install .Then use the CLI tool to convert the Trilium ETAPI spec:
mcp-generator samples/TriliumNext/etapi.openapi.yamlOr use it programmatically in your own Python code:
from openapi_mcp_generator import generator
generator.generate('samples/TriliumNext/etapi.openapi.yaml')