The MCP Server for ChatGPT macOS App allows you to connect your ChatGPT desktop application to various MCP clients like Cursor and Chatwise. This integration enables you to use ChatGPT's capabilities within supported tools through a standardized Model Context Protocol interface.
Before installing the MCP server, you'll need:
To use the MCP server properly, you need to grant accessibility permissions:
The MCP server can be installed and run using the uv
package manager:
uvx mcp-server-chatgpt-app
To configure the MCP server with Cursor:
.mcp.json
file to include the following configuration:{
"mcpServers": {
"chatgpt": {
"command": "uvx",
"args": ["mcp-server-chatgpt-app"],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}
To configure the MCP server with Chatwise:
Once configured with your client application, the server will start automatically when needed. The MCP server creates a connection between your ChatGPT macOS app and your client application, allowing them to communicate through the Model Context Protocol.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.