OpenAI MCP Server

@pierrebrunelle

Basic information

About OpenAI MCP Server

Query OpenAI models directly from Claude using MCP protocol.

OpenAI MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "openai-server": {
      "command": "python",
      "args": [
        "-m",
        "src.mcp_server_openai.server"
      ],
      "env": {
        "PYTHONPATH": "C:/path/to/your/mcp-server-openai",
        "OPENAI_API_KEY": "your-key-here"
      }
    }
  }
}

OpenAI MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

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

Frequently asked questions

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.

Comments

More AI & Agents MCP servers

早

早起鸟儿喊真人验真

shenshaoyin

早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.

BlazingCDN MCP - Content Delivery for Video, Software & Static Files

BlazingCDN

Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN

Fotor MCP

fotor

Bring ideas to life with Fotor MCP: generate and edit images, enhance product photos, and create videos, voiceovers, and music.

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain