OpenAI Universal MCP Server

This repository contains an implementation of an OpenAI Universal MCP (Model Context Protocol) server. It provides a standardized interface for interacting with OpenAI's tools and services through a unified API.

The server is built using the Universal MCP framework.

This implementation follows the MCP specification, ensuring compatibility with other MCP-compliant services and tools.

Usage

You can start using OpenAI directly from agentr.dev. Visit agentr.dev/apps and enable OpenAI.

If you have not used universal mcp before follow the setup instructions at agentr.dev/quickstart

Related MCP server: OpenAI Assistant MCP Server

Available Tools

The full list of available tools is at ./src/universal_mcp_openai/README.md

Local Development

📋 Prerequisites

Ensure you have the following before you begin:

• Python 3.11+ (recommended)

• uv (install globally with pip install uv)

🛠️ Setup Instructions

Follow the steps below to set up your development environment:

1. Sync Project Dependencies

   uv sync

   This installs all dependencies from pyproject.toml into a local virtual environment (.venv).

2. Activate the Virtual Environment

   For Linux/macOS:

   source .venv/bin/activate

   For Windows (PowerShell):

   .venv\Scripts\Activate

3. Start the MCP Inspector

   mcp dev src/universal_mcp_openai/server.py

   This will start the MCP inspector. Make note of the address and port shown in the console output.

4. Install the Application

   mcp install src/universal_mcp_openai/server.py

📁 Project Structure

.
├── src/
│   └── universal_mcp_openai/
│       ├── __init__.py       # Package initializer
│       ├── server.py            # Server entry point
│       ├── app.py            # Application tools
│       └── README.md         # List of application tools
├── tests/                    # Test suite
├── .env                      # Environment variables for local development
├── pyproject.toml            # Project configuration
└── README.md                 # This file

📄 License

This project is licensed under the MIT License.

Generated with MCP CLI — Happy coding! 🚀