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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。