A Model Context Protocol (MCP) server that enables AI assistants to interact with the ChatGPT desktop app on macOS.
input.mp4
Supported system languages for response detection:
- Korean
- English
If your macOS system language is not listed above, please follow these instructions:
- Make sure ChatGPT desktop app is running
- Run show_all_button_names.applescriptand copy the output to create an issue for language support.
- Send prompts to ChatGPT from any MCP-compatible AI assistant
- Built with Python and FastMCP
Note: This server only supports English text input. Non-English characters may not work properly.
- macOS
- ChatGPT desktop app installed and running
- Python 3.10+
- uv package manager
Simply run:
claude mcp add chatgpt-mcp uvx chatgpt-mcpThat's it! You can start using ChatGPT commands in Claude Code.
# Install with uv
uv add chatgpt-mcp# Clone the repository
git clone https://github.com/xncbf/chatgpt-mcp
cd chatgpt-mcp
# Install dependencies with uv
uv syncIf installed from PyPI, add to your MCP client configuration:
{
  "mcpServers": {
    "chatgpt": {
      "command": "uvx",
      "args": ["chatgpt-mcp"]
    }
  }
}If manually installed, add to your MCP client configuration:
{
  "mcpServers": {
    "chatgpt": {
      "command": "uv",
      "args": ["run", "chatgpt-mcp"],
      "cwd": "/path/to/chatgpt-mcp"
    }
  }
}- Open ChatGPT desktop app and make sure it's running
- Open your MCP client (Claude Code, etc.)
- Use ChatGPT commands in your AI assistant:
- "Send a message to ChatGPT"
 
The AI assistant will automatically use the appropriate MCP tools to interact with ChatGPT.
Send a prompt to ChatGPT and receive the response.
ask_chatgpt(prompt="Hello, ChatGPT!")Get the latest response from ChatGPT after sending a message.
get_chatgpt_response()Start a new chat conversation in ChatGPT.
new_chatgpt_chat()To test the MCP server locally during development:
- 
Install in editable mode uv pip install -e .
- 
Test with MCP Inspector npx @modelcontextprotocol/inspector chatgpt-mcp 
The editable installation creates a chatgpt-mcp command that directly references your source code, so any changes you make are immediately reflected without reinstalling.
You can also run the server directly:
PYTHONPATH=. uv run python -m chatgpt_mcp.chatgpt_mcpMIT