OpenAI MCP Server
@akiojin
About OpenAI MCP Server
No overview available yet
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
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 Model Context Protocol (MCP) server that enables AI assistants to interact with OpenAI’s ChatGPT API. It provides tools for generating text completions and listing available models, targeting developers who integrate AI into MCP-compatible clients.
How to use OpenAI MCP Server?
Prerequisites are Node.js 18+ and an OpenAI API key. Clone the repository, run npm install and npm run build, then create a .env file with OPENAI_API_KEY. Add the server to your MCP client configuration using the command node with args pointing to the built dist/index.js. The server exposes two tools: chat_completion and list_models.
Key features of OpenAI MCP Server
- Chat completion with multiple OpenAI models (GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, GPT-4o, o1, o1-pro, o3, o4-mini)
- List all available OpenAI models
- Configurable parameters: temperature (0–2), max tokens (default 1000), and model selection
- Built on the Model Context Protocol for seamless AI assistant integration
Use cases of OpenAI MCP Server
- Integrate ChatGPT-powered text generation into MCP-compatible AI assistants
- Dynamically select and query OpenAI models based on task requirements
- Prototype and deploy conversational agents with configurable generation settings
- Retrieve model lists for tool selection or resource planning
FAQ from OpenAI MCP Server
What models are supported?
The server supports GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, GPT-4o, o1, o1-pro, o3, and o4-mini, with GPT-4.1 as the default.
How do I configure the API key?
Copy .env.example to .env in the project root, then set OPENAI_API_KEY=your_api_key_here.
What are the system requirements?
Node.js 18 or higher and an active OpenAI API key are required.
How do I use the chat_completion tool?
Call chat_completion with required messages (array of role/content objects). Optional parameters include model, temperature (0–2, default 0.7), and max_tokens (default 1000).
Is there a tool to list models?
Yes, the list_models tool returns a list of all available OpenAI models.
Frequently asked questions
What models are supported?
The server supports GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, GPT-4o, o1, o1-pro, o3, and o4-mini, with GPT-4.1 as the default.
How do I configure the API key?
Copy `.env.example` to `.env` in the project root, then set `OPENAI_API_KEY=your_api_key_here`.
What are the system requirements?
Node.js 18 or higher and an active OpenAI API key are required.
How do I use the chat_completion tool?
Call `chat_completion` with required `messages` (array of role/content objects). Optional parameters include `model`, `temperature` (0–2, default 0.7), and `max_tokens` (default 1000).
Is there a tool to list models?
Yes, the `list_models` tool returns a list of all available OpenAI models.
Basic information
More AI & Agents MCP servers
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

Competitor Tracker & Co.
Competitor Tracker & Co.Competitor Tracker & Co. watches your competitors' websites and tells you what changed. Every week it crawls their pricing, product, messaging and corporate pages, detects the changes that matter, and files a tagged, ran
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
mcp-hfspace MCP Server 🤗
evalstateMCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Comments