mcp-google-gdrive
An MCP server that enables AI assistants to list, read, create, and manage files in Google Drive. It features automatic conversion of Google Workspace formats into Markdown, CSV, and plain text for seamless integration with AI workflows.
README
mcp-google-gdrive
An MCP server for the Google Drive API. Lets AI assistants list, read, create, and manage files in Google Drive with automatic Google Workspace format conversion (Docs to Markdown, Sheets to CSV, Slides to plain text).
Tools
| Tool | Description | Status |
|---|---|---|
| gdrive_list_files | List and search files with query filtering and pagination | Available |
| gdrive_get_metadata | Get detailed file metadata by ID | Available |
| gdrive_read_file | Read file content with automatic Workspace format conversion | Available |
| gdrive_create_file | Create a new file with content | Available |
| gdrive_create_folder | Create a new folder | Available |
| gdrive_update_file | Update existing file content | Planned |
| gdrive_delete_file | Trash or permanently delete a file | Planned |
| gdrive_move_file | Move a file between folders | Planned |
| gdrive_copy_file | Copy a file with optional rename | Planned |
| gdrive_export_doc | Export Google Doc to Markdown, HTML, or PDF | Planned |
| gdrive_export_sheet | Export Google Sheet to CSV or JSON | Planned |
| gdrive_export_slides | Export Google Slides to text or PDF | Planned |
| gdrive_create_doc | Create a Google Doc from Markdown | Planned |
| gdrive_update_doc | Update a Google Doc with Markdown content | Planned |
Prerequisites
- Node.js 18 or later
- A Google Cloud project with the Google Drive API enabled
- OAuth2 desktop application credentials
Setup
- Create a project in the Google Cloud Console and enable the Google Drive API
- Create OAuth2 credentials (Application type: Desktop app) and download the JSON file
- Save the credentials file:
mkdir -p ~/.config/mcp-google-gdrive
cp ~/Downloads/client_secret_*.json ~/.config/mcp-google-gdrive/credentials.json
chmod 600 ~/.config/mcp-google-gdrive/credentials.json
- Run the one-time authorization flow:
npx mcp-google-gdrive --auth
This opens a URL for Google consent. After granting access, paste the authorization code back into the terminal. The token is saved to ~/.config/mcp-google-gdrive/token.json.
Configuration
Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"google-drive": {
"command": "npx",
"args": ["-y", "mcp-google-gdrive"]
}
}
}
VS Code / Cursor
Add to .vscode/mcp.json:
{
"servers": {
"google-drive": {
"command": "npx",
"args": ["-y", "mcp-google-gdrive"]
}
}
}
Gemini CLI
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"google-drive": {
"command": "npx",
"args": ["-y", "mcp-google-gdrive"]
}
}
}
Authentication
The server uses OAuth2 for Google Drive access. On first run with --auth, it generates an authorization URL for browser-based consent. After authorization, tokens are stored locally at ~/.config/mcp-google-gdrive/token.json with restricted file permissions (0600).
Access tokens expire after one hour and are refreshed automatically using the stored refresh token. Token refresh is transparent and requires no user interaction.
License
MIT
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.
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.
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.
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.