ChatGPT Responses

by billster45

4 stars

700 downloads

Not rated

GitHub

About

Bridges Claude Desktop with ChatGPT API, enabling direct access to standard ChatGPT interactions and web search-enabled queries with conversation continuity through response IDs.

Details

Author: billster45
Repository: billster45/mcp-chatgpt-responses
GitHub stars: 4
Downloads: 700
Categories: Communication, Other, AI, Productivity, Developer Tools, Design, Community, Search, Infrastructure, API
Tags: #web, #integration

- 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

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name ChatGPT Responses

Command (node, npx, python, etc.) uv
Arguments
- Argument 1 --directory
- Argument 2 \path\to\mcp-chatgpt-responses
- Argument 3 run
- Argument 4 chatgpt_server.py
Environment
- MAX_TOKENS 1000
- DEFAULT_MODEL gpt-4o
- OPENAI_API_KEY your-api-key-here
- DEFAULT_TEMPERATURE 0.7
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

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

JSON

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

JSON

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

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

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

JSON

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

JSON

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

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

From the repository

1. Clone this repository:

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

   cd mcp-chatgpt-responses

2. Set up a virtual environment and install dependencies using uv:

   uv venv

   .venv\\Scripts\\activate

   uv pip install -r requirements.txt

To install ChatGPT Server for Claude Desktop automatically via Smithery:

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

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.

`ask_chatgpt`

Send a prompt to ChatGPT and get a response. Parameters: prompt (string), model (string), temperature (float), max_output_tokens (int), response_id (string)

`ask_chatgpt_with_web_search`

Send a prompt to ChatGPT with web search enabled to get up-to-date information. Parameters: prompt (string), model (string), temperature (float), max_output_tokens (int), response_id (string)

The MCP server provides the following tools:

1. ask_chatgpt(prompt, model, temperature, max_output_tokens, response_id) - Send a prompt to ChatGPT and get a response

2. 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

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

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

Linux

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

Macos

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

Windows

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

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

Setup Instructions

Installing via Smithery

To install ChatGPT Server for Claude Desktop automatically via Smithery:

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

1. Clone this repository:

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

   cd mcp-chatgpt-responses

2. Set up a virtual environment and install dependencies using uv:

   uv venv

   .venv\\Scripts\\activate

   uv pip install -r requirements.txt

Using with Claude Desktop

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

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

   {

     "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"

         }

       }

     }

   }

3. Restart Claude Desktop.

4. 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:

1. ask_chatgpt(prompt, model, temperature, max_output_tokens, response_id) - Send a prompt to ChatGPT and get a response

2. 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.

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:

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

License

MIT License

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

ask_chatgpt

ask_chatgpt_with_web_search

Claude Desktop / Cursor

Linux

Macos

Windows

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

Install

More like this

Sequential Thinking

Slack

Filesystem

EverArt

Google Drive

Context 7

`ask_chatgpt`

`ask_chatgpt_with_web_search`