Google Drive MCP Server

What is Google Drive MCP Server?

A Model Context Protocol (MCP) server that provides a standardized interface for AI systems to access and manipulate files in Google Drive via the Google Drive API.

How to use Google Drive MCP Server?

Install Python 3.8+, enable the Google Drive API in a Google Cloud project, create a service account, and download its JSON key. Clone the repository, create a virtual environment, install dependencies, copy .env.example to .env, and configure HOST, PORT, and GOOGLE_SERVICE_ACCOUNT_FILE. Run python main.py --transport sse or use Docker with docker-compose up. Connect an MCP client using transport sse and serverUrl http://localhost:8055/sse.

Key features of Google Drive MCP Server

• List, upload, download, and delete files
• Create folders and organize content
• Share files with specific users and manage permissions
• Handle large file listings with pagination support
• Detailed error reporting for easier debugging
• Debug API connection tool

Use cases of Google Drive MCP Server

• AI assistants managing Google Drive files programmatically
• Automated file upload and sharing workflows
• Retrieving metadata and content of specific files
• Debugging Google Drive API connectivity issues

FAQ from Google Drive MCP Server

What are the prerequisites to use this server?

Python 3.8 or later, a Google Cloud project with the Drive API enabled, and a service account with appropriate permissions. The service account JSON key file must be downloaded.

How do I connect an MCP client to this server?

Configure the client with transport sse and serverUrl http://localhost:8055/sse. Ensure the server is running with the --transport sse flag.

Where does my data reside when using this server?

All file operations target Google Drive directly; the server only mediates requests via the Google Drive API. The service account key file is stored locally as configured.

What security considerations should I be aware of?

The service account JSON file contains sensitive credentials – never commit it to version control. Use environment variables for all sensitive configuration. Consider additional authentication if deploying publicly.

How can I run the server locally versus using Docker?

Locally: python main.py --transport sse. With Docker: docker-compose up. Both require the service account key file to be available at the path specified in .env.