Google Drive MCP Server
Enables searching, retrieving, and managing files in Google Drive using a service account. Supports file search with query syntax, metadata retrieval, folder operations, file moving, and folder creation.
README
Google Drive MCP Server
An MCP (Model Context Protocol) server that enables Claude to interact with your Google Drive. Works with Claude Web via OAuth2 authentication.
Features
- List files - Browse your Drive files and folders
- Search - Full-text search across your Drive
- Read files - Read content from text files, Google Docs, and Sheets
- Create folders - Organize your Drive with new folders
- Create files - Create text files, JSON files, or Google Docs
Tools
| Tool | Description |
|---|---|
list_drive_files |
List files in Drive, optionally filtered by folder, MIME type, or query |
get_file_info |
Get detailed metadata about a specific file |
search_drive |
Search files by name or content |
read_file |
Read the content of a file (supports text files, Google Docs, Sheets as CSV) |
create_folder |
Create a new folder |
create_file |
Create a new file with text content |
Architecture
Claude Web → OAuth2 → Your Cloud Run Server → Google Drive API
↓
Firestore (tokens)
Secret Manager (credentials)
See ARCHITECTURE.md for detailed documentation on how to build similar MCP servers.
Quick Start
Prerequisites
- Google Cloud account with billing enabled
gcloudCLI installed and authenticated- Node.js 20+
1. Clone and Install
git clone https://github.com/matty-v/google-drive-mcp.git
cd google-drive-mcp
npm install
2. Set Up Google Cloud
export PROJECT_ID="your-project-id"
export REGION="us-central1"
gcloud config set project $PROJECT_ID
# Enable required APIs
gcloud services enable \
run.googleapis.com \
secretmanager.googleapis.com \
firestore.googleapis.com \
drive.googleapis.com
# Create Firestore database
gcloud firestore databases create --location=$REGION
3. Create OAuth Credentials
- Go to Google Cloud Console - Credentials
- Click Create Credentials → OAuth client ID
- Application type: Web application
- Name:
MCP Drive Server - Leave redirect URIs empty for now (we'll add after deployment)
- Copy the Client ID and Client Secret
4. Configure OAuth Consent Screen
- Go to OAuth consent screen
- User Type: External
- Fill in required fields
- Add scopes:
drive,drive.file,userinfo.email - Add yourself as a test user
5. Store Secrets
echo -n "YOUR_CLIENT_ID" | gcloud secrets create oauth-client-id --data-file=-
echo -n "YOUR_CLIENT_SECRET" | gcloud secrets create oauth-client-secret --data-file=-
6. Deploy
npm run build
gcloud run deploy mcp-drive-server \
--source . \
--region $REGION \
--allow-unauthenticated \
--set-env-vars "GCP_PROJECT=$PROJECT_ID"
7. Update OAuth Redirect URI
-
Get your service URL:
gcloud run services describe mcp-drive-server --region $REGION --format="value(status.url)" -
Go back to Google Cloud Console - Credentials
-
Edit your OAuth client
-
Add authorized redirect URI:
https://YOUR-SERVICE-URL/google/callback
8. Update Cloud Run with BASE_URL
SERVICE_URL=$(gcloud run services describe mcp-drive-server --region $REGION --format="value(status.url)")
gcloud run services update mcp-drive-server \
--region $REGION \
--set-env-vars "BASE_URL=$SERVICE_URL,GCP_PROJECT=$PROJECT_ID"
9. Grant IAM Permissions
SA_EMAIL="${PROJECT_ID}-compute@developer.gserviceaccount.com"
# Firestore access
gcloud projects add-iam-policy-binding $PROJECT_ID \
--member="serviceAccount:$SA_EMAIL" \
--role="roles/datastore.user"
# Secret Manager access
gcloud secrets add-iam-policy-binding oauth-client-id \
--member="serviceAccount:$SA_EMAIL" \
--role="roles/secretmanager.secretAccessor"
gcloud secrets add-iam-policy-binding oauth-client-secret \
--member="serviceAccount:$SA_EMAIL" \
--role="roles/secretmanager.secretAccessor"
10. Connect to Claude Web
- Go to claude.ai
- Settings → Integrations
- Add MCP server with your Cloud Run URL
- Click Connect and authenticate with Google
Usage Examples
Once connected, you can ask Claude:
- "List my recent Google Drive files"
- "Search my Drive for documents about quarterly reports"
- "Read the content of my meeting notes document"
- "What's in my budget spreadsheet?"
- "Create a folder called 'Projects' in my Drive"
- "Create a file called 'notes.txt' with my meeting notes"
- "Create a Google Doc called 'Project Plan' with an outline"
Security
- OAuth2 with PKCE - Secure authorization flow
- Per-user authentication - Each user authenticates with their own Google account
- Token encryption - Tokens stored encrypted in Firestore
- Minimal scopes - Only requests necessary Drive permissions
- No credential storage - Your Google password never touches the server
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run locally (requires environment variables)
npm start
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.