What is Openapi Mcp Server

openapi_mcp_server is a project that installs the Model Context Protocol Server (MCP), which provides configured REST APIs as context for Large Language Models (LLMs). It enables LLMs to interact with REST APIs and perform API calls using prompts.

Use cases

Use cases for openapi_mcp_server include integrating LLMs with external APIs, automating API interactions, and enhancing LLM capabilities by providing them with real-time data from REST APIs.

How to use

To use openapi_mcp_server, install the package via pip with ‘pip install openapi_mcp_server’. Create a .env file with the required values for OPENAPI_SPEC_PATH and API_BASE_URL. Then, test the server by running ‘uv run openapi_mcp_server’ from the directory containing the .env file.

Key features

Key features include support for HTTP API calls (GET, PUT, POST, PATCH), configurable environment variables for API specifications, and the ability to whitelist or blacklist specific API operations.

Where to use

undefined

OpenAPI MCP Server

Overview

• This project will install MCP - Model Context Protocol Server, that provides configured REST API’s as context to LLM’s.
• Using this we can enable LLMs to interact with RestAPI’s and perform REST API call’s using LLM prompts.
• Currently we support HTTP API Call’s GET/PUT/POST/PATCH.

Installation

• Install package

  pip install openapi_mcp_server
  

• Create .env in a folder with minimum values for OPENAPI_SPEC_PATH & API_BASE_URL. Sample file available here
• Test openapi_mcp_server server using uv run openapi_mcp_server from the above folder.

Claud Desktop

• Configuration details for Claud Desktop
  

Configuration

• List of available environment variables
  • DEBUG: Enable debug logging (optional default is False)
  • OPENAPI_SPEC_PATH: Path to the OpenAPI document. (required)
  • API_BASE_URL: Base URL for the API requests. (required)
  • API_HEADERS: Headers to include in the API requests (optional)
  • API_WHITE_LIST: White Listed operationId in list format [“operationId1”, “operationId2”] (optional)
  • API_BLACK_LIST: Black Listed operationId in list format [“operationId3”, “operationId4”] (optional)
  • HTTP_PROXY: HTTP Proxy details (optional)
  • HTTPS_PROXY: HTTPS Proxy details (optional)
  • NO_PROXY: No Proxy details (optional)

Contributing

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

License

This project is licensed under the terms of the MIT license.

Github Stars

Appendix

UV

mkdir -m777 openapi_mcp_server
cd openapi_mcp_server
uv init
uv add mcp[cli] pydantic python-dotenv requests
uv add --dev twine setuptools
uv sync
uv run openapi_mcp_server
uv build
pip install --force-reinstall --no-deps .\dist\openapi_mcp_server-*fileversion*.whl
export TWINE_USERNAME="rahgadda"
export TWINE_USERNAME="<<API Key>>"
uv run twine upload --verbose dist/*

Reference

• UV Overview