MCP ChatGPT Server

Name: MCP ChatGPT Server
Author: billster45

@billster45

Repository

About MCP ChatGPT Server

MCP server for access to OpenAI's ChatGPT API with Responses API for conversation management

Basic information

Config

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

{
  "mcpServers": {
    "mcp-chatgpt-responses": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@billster45/mcp-chatgpt-responses",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

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 MCP ChatGPT Server?

It is an MCP server that enables Claude Desktop to access OpenAI’s ChatGPT API directly. It allows users to send prompts to ChatGPT, including with web search, and maintains conversation state automatically using OpenAI’s Responses API.

How to use MCP ChatGPT Server?

Install via Smithery or by cloning the repository, setting up a Python virtual environment with uv, and configuring Claude Desktop to run the server with your OpenAI API key. Then ask Claude to use the tools ask_chatgpt or ask_chatgpt_with_web_search to interact with ChatGPT.

Key features of MCP ChatGPT Server

Call ChatGPT API with customizable parameters (model, temperature, max tokens).
Maintain conversation state across messages using OpenAI’s Responses API.
Enable web search for up-to-date information from the internet.
Use your own OpenAI API key.
Let Claude and ChatGPT converse in a long-running discussion.
Provide two tools: ask_chatgpt and ask_chatgpt_with_web_search.

Use cases of MCP ChatGPT Server

Ask ChatGPT questions directly from Claude when Claude lacks information.
Have a turn-taking conversation between Claude and ChatGPT on any topic.
Get up-to-date information from the web through ChatGPT’s web search capability.
Plan activities based on current data (e.g., weather) by using web search in an agentic loop.

FAQ from MCP ChatGPT Server

How does this server maintain conversation state?

It uses OpenAI’s Responses API, which automatically manages conversation history on OpenAI’s servers, simplifying code and providing reliable context tracking.

What are the prerequisites for using this server?

Python 3.10 or higher, the Claude Desktop app, an OpenAI API key, and the uv package manager are required.

How do I configure the server with Claude Desktop?

Add the provided JSON configuration to your Claude Desktop config file, specifying the server command, directory, and environment variables (e.g., OPENAI_API_KEY, DEFAULT_MODEL, DEFAULT_TEMPERATURE, MAX_TOKENS), then restart Claude Desktop.

What tools does the server provide?

Two tools: ask_chatgpt(prompt, model, temperature, max_output_tokens, response_id) for standard prompts, and ask_chatgpt_with_web_search(…) for prompts that include web search to retrieve current information.

Where does conversation data live?

Conversation state is stored on OpenAI’s servers via the Responses API, not locally on the user’s machine.

Comments

More AI & Agents MCP servers

Intervals.icu MCP Server

mvilanova

Model Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.

311

MCP Client for Ollama (ollmcp)

jonigl

Harness 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

768

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797