Google Drive MCP Server
Enables Claude to manage Google Drive files and folders through natural language commands. Supports creating folders, moving/renaming files, retrieving file metadata, and listing folder contents with secure OAuth authentication.
README
Google Drive MCP Server
Give Claude the ability to manage your Google Drive files through the Model Context Protocol (MCP).
Available Tools
Once configured, Claude can:
- create_drive_folder - Create new folders in your Drive
- move_drive_file - Move files/folders between locations
- rename_drive_file - Rename any file or folder
- get_drive_file_info - Get metadata about files
- list_drive_folder_contents - See what's inside folders
Example Usage
"Create a folder structure for organizing my Drive: Personal, Work, and Projects"
"Move all the documents with 'meeting notes' in the name to the Work folder"
"Show me what's in my root Drive folder"
Setup
Prerequisites
- Python 3.10+
- Google account
- Claude Desktop app
1. Google Cloud Setup
- Go to Google Cloud Console
- Create a new project or select existing one
- Enable the Google Drive API
- Create OAuth 2.0 credentials:
- Go to "APIs & Services" → "Credentials"
- Click "Create Credentials" → "OAuth client ID"
- Choose "Desktop app"
- Download the JSON file
Might need to add yourself as a test user under "OAuth consent screen" tab.
2. Install Dependencies
# Clone this repository
git clone https://github.com/danbugs/google-drive-mcp.git
cd google-drive-mcp
# Create virtual environment
python -m venv venv
# Activate virtual environment
# Windows:
venv\Scripts\activate
# macOS/Linux:
source venv/bin/activate
# Install dependencies
pip install -r requirements.txt
3. Setup Credentials
# Create credentials directory
mkdir ~/.google-drive-mcp # or %USERPROFILE%\.google-drive-mcp on Windows
# Move your downloaded credentials file
# Rename it to credentials.json and place in ~/.google-drive-mcp/
4. Test Authentication
Run the test script to complete OAuth setup:
python test_auth.py
This will open a browser window for Google authentication and create the required token.json file.
5. Configure Claude Desktop
Edit your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Add the MCP server configuration:
{
"mcpServers": {
"google-drive": {
"command": "/path/to/your/venv/bin/python",
"args": ["/path/to/your/google_drive_mcp_server.py"]
}
}
}
Replace /path/to/your/ with your actual paths. On Windows, use venv\Scripts\python.exe instead.
6. Restart Claude Desktop
Quit and restart Claude Desktop, then test with:
"Can you list the contents of my Google Drive root folder?"
Security
- OAuth credentials stored locally in
~/.google-drive-mcp/ - Only accessible through Claude Desktop via MCP
- Standard Google OAuth security model
- Revoke access anytime from Google Account settings
Troubleshooting
"Credentials file not found"
- Ensure
credentials.jsonis in~/.google-drive-mcp/ - Check file permissions
"Module not found" errors
- Activate the virtual environment
- Re-run
pip install -r requirements.txt
Claude doesn't see the tools
- Verify
claude_desktop_config.jsonsyntax is valid JSON - Use absolute paths, not relative ones
- Restart Claude Desktop completely
- Check Claude Desktop logs: Help → "Show Logs"
Authentication issues
- Delete
~/.google-drive-mcp/token.jsonand re-runtest_auth.py - Ensure Google Drive API is enabled in Cloud Console
Resources
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.