MCP.so
Sign In
Servers

OpenAI MCP Server

@pierrebrunelle

Query OpenAI models directly from Claude using MCP protocol.

Overview

What is OpenAI MCP Server?

OpenAI MCP Server is a lightweight bridge that lets Claude (or any MCP client) send prompts to OpenAI models and receive responses, using the Model Context Protocol. It is intended for developers who want to combine Claude’s interface with OpenAI’s language models.

How to use OpenAI MCP Server?

Add the server configuration to your claude_desktop_config.json file, specifying the Python command, the module path, and the environment variable OPENAI_API_KEY. Then launch Claude Desktop, and the server will be available as an MCP tool. Development and testing require cloning the repository and installing the package with pip install -e ..

Key features of OpenAI MCP Server

  • Directly queries OpenAI models from Claude
  • Simple setup via claude_desktop_config.json
  • Runs as a standard Python MCP server
  • Tested with pytest -v test_openai.py -s
  • Open source under the MIT license

Use cases of OpenAI MCP Server

  • Enabling Claude to answer questions using OpenAI’s GPT models
  • Comparing outputs from OpenAI models side‑by‑side in Claude
  • Using Claude’s interface to access OpenAI for specialized tasks
  • Rapid prototyping of multi‑model workflows without leaving the chat

FAQ from OpenAI MCP Server

What runtime does OpenAI MCP Server require?

Python 3 must be installed on your system. The server is invoked with python -m src.mcp_server_openai.server.

How do I configure the server?

Edit claude_desktop_config.json to include the server entry, set the PYTHONPATH to the server directory, and provide your OPENAI_API_KEY environment variable.

How can I test that the server works?

From the project root, run pytest -v test_openai.py -s. A successful test prints an OpenAI response and passes all checks.

What OpenAI models are supported?

The server works with any OpenAI model accessible via the standard API—no model‑specific restrictions are mentioned in the README.

Does the server support streaming or advanced features?

The README does not describe streaming, function calling, or other advanced OpenAI API features. It only covers sending a prompt and receiving a reply.

More from AI & Agents