mcp-chatgpt-responsesMCP server for access to OpenAI's ChatGPT API with Responses API for conversation management
Overview
Key features
- Call ChatGPT API with customizable parameters
- Aks Claude and ChatGPT to talk to each other in long-running discussions
- Configure model versions, temperature, and other parameters
- Use web search to get up-to-date information
- Uses OpenAI's Responses API for automatic conversation state management
- Use your own OpenAI API key
Pricing
- Model
- Free
- Category
- MCP Servers
- Rating
- No reviews yet
Use cases
Basic ChatGPT Usage
Use the ask_chatgpt tool to answer questions, such as 'What is the best way to learn Python?'
Conversation with ChatGPT
Use the ask_chatgpt tool to have a two-way conversation with ChatGPT about a specific topic
Web Search Integration
Use the ask_chatgpt_with_web_search tool to answer questions that benefit from up-to-date information, such as 'What are the latest developments in quantum computing?'
Pros & Cons
Pros
- Enables direct access to ChatGPT API from Claude Desktop
- Supports customizable parameters for ChatGPT API calls
- Utilizes OpenAI's Responses API for automatic conversation state management
- Allows use of own OpenAI API key
- Supports long-running discussions between Claude and ChatGPT
Cons
- Requires Python 3.10 or higher
- Requires Claude Desktop application
- Requires OpenAI API key
- May have limitations based on OpenAI API usage policies
Reviews
Sign in to leave a review.
No reviews yet. Be the first!
Q&A
Is web search integration optional when sending prompts to ChatGPT?
Yes, the server offers tools to send prompts with or without web search enabled, letting you choose whether to retrieve up‑to‑date information for each request.
Asked by Femi Adebayo · Nov 30, 2025
How does the server manage conversation history between Claude and ChatGPT?
It leverages OpenAI’s Responses API, which automatically tracks conversation state, allowing long‑running discussions without you having to code manual history handling.
Asked by Nikolai Petrenko · Sep 21, 2025
Can I use my own OpenAI API key with the MCP server, and how does it affect usage limits?
Yes, you supply your own OpenAI API key, which means you are subject to OpenAI’s usage policies and rate limits. The server does not provide its own quota; all costs and limits are applied to your key.
Asked by Fumiko Sato · Sep 16, 2025
What Python version and environment are required to run the MCP server?
The server requires Python 3.10 or higher and should be set up in a virtual environment. Installation can be done via Smithery or by cloning the repo and manually configuring the environment.
Asked by Jana Krejčí · Aug 15, 2025
Ask a question
MCP Servers alternatives

Open-source MCP server that lets LLMs drive real browsers via Playwright and accessibility snapshots.

Python agent framework from the Pydantic team for building type-safe GenAI apps.

Adaptive memory layer that helps AI agents learn from context over time.

AI email assistant that organizes, drafts replies, and helps you reach inbox zero faster.

Open-source 24/7 local screen and audio recording for building context-aware AI apps

TypeScript library for building and orchestrating AI agents with tools, memory, and multi-agent workflows.

Bringing the bankless onchain API to MCP

Python tool for converting files and office documents to Markdown.
Trending now

Accurate Homework Help with Full Explanations

Document intelligence API that parses, splits, OCRs, and extracts structured data from complex PDFs, slides, and spreadsheets.

Open multimodal 12B model handling interleaved images and text with a 128K context window.

Sponsored answers, paid per click.
