MCPs
MCP ChatGPT Server

MCP ChatGPT Server

Enables direct access to OpenAI's ChatGPT API from Claude Desktop via the Model Context Protocol.

Stars

Forks

Watchers

Issues

MCP ChatGPT Server runs as an MCP-compliant server, allowing users to access OpenAI's ChatGPT API seamlessly within Claude Desktop. It supports customizable model parameters, automated conversation state management, integrated web search for up-to-date information, and facilitates interactive discussions between Claude and ChatGPT. Users can configure model selection, temperature, token limits, and use their own OpenAI API keys.

Key Features

Direct ChatGPT API access from Claude Desktop

Configurable model selection and parameters

Supports long-running multi-model conversations

Integrates web search for real-time information

Automatic conversation state management

User-provided OpenAI API key support

Installation via Smithery package manager

Customizable environment variables for advanced control

Python 3.10+ compatibility

Easy setup and integration with Claude Desktop

Use Cases

Seamless interaction with ChatGPT from Claude Desktop

Facilitating real-time information retrieval through web search

Enabling in-depth, stateful conversations involving multiple AI models

Allowing users to specify and tune AI response parameters

Automated conversation memory and context retention

Setting up collaborative or comparative AI-to-AI discussions

Testing and evaluating OpenAI models within a desktop workflow

Personal or organizational use with proprietary OpenAI API keys

Building advanced AI-powered productivity or research tools

Providing accessible natural language querying for end-users

README

MCP ChatGPT Server

This MCP server allows you to access OpenAI's ChatGPT API directly from Claude Desktop.

📝 Read about why I built this project: I Built an AI That Talks to Other AIs: Demystifying the MCP Hype

Features

Call the ChatGPT API with customisable parameters
Aks Claude and ChatGPT to talk to each other in a long running discussion!
Configure model versions, temperature, and other parameters
Use web search to get up-to-date information from the internet
Uses OpenAI's Responses API for automatic conversation state management
Use your own OpenAI API key

Setup Instructions

Installing via Smithery

To install ChatGPT Server for Claude Desktop automatically via Smithery:

bash

npx -y @smithery/cli install @billster45/mcp-chatgpt-responses --client claude

Prerequisites

Python 3.10 or higher
Claude Desktop application
OpenAI API key
uv for Python package management

Installation

Clone this repository:

bash

git clone https://github.com/billster45/mcp-chatgpt-responses.git
cd mcp-chatgpt-responses

Set up a virtual environment and install dependencies using uv:
bash
```
uv venv
```
bash
```
.venv\\Scripts\\activate
```
bash
```
uv pip install -r requirements.txt
```

Using with Claude Desktop

Configure Claude Desktop to use this MCP server by following the instructions at: MCP Quickstart Guide

Add the following configuration to your Claude Desktop config file (adjust paths as needed):

json

{
  "mcpServers": {
    "chatgpt": {
      "command": "uv",
      "args": [
        "--directory",
        "\\path\\to\\mcp-chatgpt-responses",
        "run",
        "chatgpt_server.py"
      ],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here",
        "DEFAULT_MODEL": "gpt-4o",
        "DEFAULT_TEMPERATURE": "0.7",
        "MAX_TOKENS": "1000"
      }
    }
  }
}

Restart Claude Desktop.
You can now use the ChatGPT API through Claude by asking questions that mention ChatGPT or that Claude might not be able to answer.

Available Tools

The MCP server provides the following tools:

ask_chatgpt(prompt, model, temperature, max_output_tokens, response_id) - Send a prompt to ChatGPT and get a response
ask_chatgpt_with_web_search(prompt, model, temperature, max_output_tokens, response_id) - Send a prompt to ChatGPT with web search enabled to get up-to-date information

Example Usage

Basic ChatGPT usage:

Tell Claude to ask ChatGPT a question!

Use the ask_chatgpt tool to answer: What is the best way to learn Python?

Tell Claude to have a conversation with ChatGPT:

Use the ask_chatgpt tool to have a two way conversation between you and ChatGPT about the topic that is most important to you.

Note how in a turn taking conversation the response id allows ChatGPT to store the history of the conversation so its a genuine conversation and not just as series of API calls. This is called conversation state.

With web search:

For questions that may benefit from up-to-date information:

Use the ask_chatgpt_with_web_search tool to answer: What are the latest developments in quantum computing?

Now try web search in agentic way to plan your perfect day out based on the weather!

Use the ask_chatgpt_with_web_search tool to find the weather tomorrow in New York, then based on that weather and what it returns, keep using the tool to build up a great day out for someone who loves food and parks

How It Works

This tool utilizes OpenAI's Responses API, which automatically maintains conversation state on OpenAI's servers. This approach:

Simplifies code by letting OpenAI handle the conversation history
Provides more reliable context tracking
Improves the user experience by maintaining context across messages
Allows access to the latest information from the web with the web search tool

License

MIT License

Star History

Repository Owner

billster45

User

Repository Details

Language Python

Default Branch main

Size 25 KB

Contributors 3

MCP Verified Nov 12, 2025

Programming Languages

Python

94.87%

Dockerfile

5.13%

Related MCPs

Discover similar Model Context Protocol servers

MCP OpenAI Server

Seamlessly connect OpenAI's models to Claude via Model Context Protocol.

MCP OpenAI Server acts as a Model Context Protocol (MCP) bridge allowing Claude Desktop to access and interact with multiple OpenAI chat models. It enables users to leverage models such as GPT-4o and O1 directly from Claude using a straightforward message-passing interface. The server supports easy integration through configuration and provides basic error handling. Designed for use with Node.js and requiring an OpenAI API key, it is tailored for macOS with support for other platforms in progress.

⭐ 69
MCP
mzxrai/mcp-openai

OpenAI MCP Server

Bridge between Claude and OpenAI models using the MCP protocol.

OpenAI MCP Server enables direct querying of OpenAI language models from Claude via the Model Context Protocol (MCP). It provides a configurable Python server that exposes OpenAI APIs as MCP endpoints. The server is designed for seamless integration, requiring simple configuration updates and environment variable setup. Automated testing is supported to verify connectivity and response from the OpenAI API.

⭐ 77
MCP
pierrebrunelle/mcp-server-openai

any-chat-completions-mcp

Integrate multiple AI chat providers with OpenAI-compatible MCP server.

any-chat-completions-mcp is a TypeScript-based server implementing the Model Context Protocol (MCP) to connect popular AI chat providers like OpenAI, Perplexity, Groq, xAI, and PyroPrompts via a unified interface. It relays chat/completion requests to any OpenAI SDK-compatible API, allowing users to easily access multiple AI services through the same standardized protocol. The server can be configured for different providers by setting environment variables and integrates with both Claude Desktop and LibreChat.

⭐ 143
MCP
pyroprompts/any-chat-completions-mcp

Perplexity MCP Server

MCP Server integration for accessing the Perplexity API with context-aware chat completion.

Perplexity MCP Server provides a Model Context Protocol (MCP) compliant server that interfaces with the Perplexity API, enabling chat completion with citations. Designed for seamless integration with clients such as Claude Desktop, it allows users to send queries and receive context-rich responses from Perplexity. Environment configuration for API key management is supported, and limitations with long-running requests are noted. Future updates are planned to enhance support for client progress reporting.

⭐ 85
MCP
tanigami/mcp-server-perplexity

gqai

Expose GraphQL operations as Model Context Protocol (MCP) tools for AI models.

gqai is a lightweight proxy that converts GraphQL operations into MCP-compatible tools, enabling integration with AI systems such as ChatGPT, Claude, and Cursor. It automatically discovers and exposes GraphQL queries and mutations as callable tools via an MCP server, powered by your existing GraphQL backend. Configuration is managed via standard .graphqlrc.yml and .graphql files, with support for dynamic endpoints and environment variables.

⭐ 21
MCP
fotoetienne/gqai

mcp-graphql

Enables LLMs to interact dynamically with GraphQL APIs via Model Context Protocol.

mcp-graphql provides a Model Context Protocol (MCP) server that allows large language models to discover and interact with GraphQL APIs. The implementation facilitates schema introspection, exposes the GraphQL schema as a resource, and enables secure query and mutation execution based on configuration. It supports configuration through environment variables, automated or manual installation options, and offers flexibility in using local or remote schema files. By default, mutation operations are disabled for security, but can be enabled if required.

⭐ 319
MCP
blurrah/mcp-graphql

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

MCP ChatGPT Server

Key Features

Use Cases

README

MCP ChatGPT Server

Features

Setup Instructions

Installing via Smithery

Prerequisites

Installation

Using with Claude Desktop

Available Tools

Example Usage

Basic ChatGPT usage:

With web search:

How It Works

License

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs