About Chatgpt MCP
Chatgpt MCP is an MCP server published by yowmamasita in the Communication category: enhanced MCP server for ChatGPT with dynamic button detection and improved response handling.
Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/yowmamasita/chatgpt-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (2)
ask_chatgptSend a prompt to ChatGPT and get the complete response
Parameters not published.
new_chatStart a fresh conversation in ChatGPT
Parameters not published.
Ask AI
Ask AI about Chatgpt MCP
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
- ✓License declaredUsable under a stated license.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
3 checks have not been run yet.
README
ChatGPT MCP Plus
An enhanced Model Context Protocol (MCP) server that enables AI assistants to interact with the ChatGPT desktop app on macOS.
Based on the original chatgpt-mcp by @xncbf
What's New in Plus Version
- Dynamic Button Detection: Reliable UI interaction without hardcoded positions
- Enhanced Response Handling: Waits for complete responses using button state monitoring
- New Chat Tool: Start fresh conversations with a single command
- Improved Reliability: Better error handling and state detection
Features
- Send prompts to ChatGPT and receive complete responses
- Start new chat conversations to clear context
- Automatic response detection using button state monitoring
- Built with Python and FastMCP
Note: This server only supports English text input. Non-English characters may not work properly.
Installation
Prerequisites
- macOS
- ChatGPT desktop app installed and running
- Python 3.10+
- uv package manager
For Claude Code Users
Simply run:
claude mcp add chatgpt-mcp-plus uvx chatgpt-mcp-plus
That's it! You can start using ChatGPT commands in Claude Code.
For Other MCP Clients
Step 1: Install the MCP Server
Option A: Install from PyPI (Recommended)
# Install with uv
uv add chatgpt-mcp-plus
Option B: Manual Installation
# Clone the repository
git clone https://github.com/yowmamasita/chatgpt-mcp
cd chatgpt-mcp
# Install dependencies with uv
uv sync
Step 2: Configure Your MCP Client
If installed from PyPI, add to your MCP client configuration:
{
"mcpServers": {
"chatgpt-plus": {
"command": "uvx",
"args": ["chatgpt-mcp-plus"]
}
}
}
If manually installed, add to your MCP client configuration:
{
"mcpServers": {
"chatgpt-plus": {
"command": "uv",
"args": ["run", "chatgpt-mcp-plus"],
"cwd": "/path/to/chatgpt-mcp"
}
}
}
Usage
- Open ChatGPT desktop app and make sure it's running
- Open your MCP client (Claude Code, etc.)
- Use ChatGPT commands in your AI assistant:
Available Tools
-
ask_chatgpt: Send a prompt to ChatGPT and get the complete response
Example: "Ask ChatGPT to explain quantum computing" -
new_chat: Start a fresh conversation in ChatGPT
Example: "Start a new chat in ChatGPT"
The AI assistant will automatically use the appropriate MCP tools to interact with ChatGPT.
Tool Details
ask_chatgpt
Send a prompt to ChatGPT and wait for the complete response.
Parameters:
prompt(string): The text to send to ChatGPT
Returns: ChatGPT's complete response text
Example:
response = await ask_chatgpt("What is the capital of France?")
# Returns: "The capital of France is Paris..."
new_chat
Start a new conversation in ChatGPT, clearing any previous context.
Parameters: None
Returns: Success message
Example:
result = await new_chat()
# Returns: "Successfully started a new chat conversation"
Acknowledgments
This project is based on the original chatgpt-mcp by @xncbf. The Plus version adds enhanced features including dynamic button detection, improved response handling, and new chat functionality.
License
MIT
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.