About ChatGPT Memory MCP Server
ChatGPT Memory MCP Server makes ChatGPT's memory available as shared information beyond a single model provider. It is for people connecting applications such as Claude Desktop to that memory through MCP.
Key features
- 01Access ChatGPT memory through MCP
- 02Share memory beyond one model provider
- 03Python-based server setup
Use cases
- 01Connect ChatGPT memory to Claude Desktop
- 02Make ChatGPT memory available to another MCP-connected application
MCP support
Exposes ChatGPT memory through an MCP server that can be linked to applications such as Claude Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEChatGPT Memory MCP Server
Under MIT License
Since ChatGPT has memory it becomes a valuable data source for other models; I'm facilitating a shared memory outside of a single model provider.
To use this MCP server:
- Clone the repository
- Install the required packages using
pip install -r requirements.txt - Set up the environment variables
- You can use the path to your Chrome executable (find this by typing
chrome://versionin the address bar of Chrome) or set it toNoneto use the default path.
- You can use the path to your Chrome executable (find this by typing
- Link the server with an application, for example with Claude Desktop App, follow instructions here: https://modelcontextprotocol.io/quickstart/server#testing-your-server-with-claude-for-desktop
- Here is an example Claude config file:
{ "mcpServers": { "chatgpt_memory": { "command": "C:\path_to_where_you_cloned_this_repo\\.venv\\Scripts\\python.exe", "args": [ "C:\path_to_where_you_cloned_this_repo\\ChatGPT_MCPserver.py" ] } } }
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.