Google Docs MCP Server
Enables Claude to read, create, and update Google Docs through OAuth authentication. Deployed as a remote Next.js server on Vercel with support for multiple users and secure API key management.
README
Google Docs MCP Server (Next.js)
A remote Model Context Protocol (MCP) server that provides Google Docs integration for Claude Desktop, built with Next.js and deployed on Vercel.
Features
- Remote MCP Server: Deployed on Vercel with SSE transport
- Google OAuth: Secure authentication with Google Docs and Drive permissions
- Web Dashboard: User-friendly interface for managing API keys
- Multi-user: Support for multiple users with isolated access
- API Key Management: Secure token-based authentication for MCP clients
Architecture
User Browser → Next.js App → Google OAuth → Database (User/Tokens)
Claude Desktop → MCP SSE Transport → API Key Auth → Google APIs
Setup
1. Google Cloud Console Setup
- Create a new project in Google Cloud Console
- Enable Google Docs API and Google Drive API
- Create OAuth 2.0 credentials:
- Application type: Web application
- Authorized redirect URIs:
https://your-app.vercel.app/api/auth/callback/google
- Copy Client ID and Client Secret
2. Database Setup
Create a PostgreSQL database (recommended: Neon or Supabase)
3. Redis Setup
Create a Redis instance (required for Vercel MCP adapter). Recommended: Upstash
4. Deploy to Vercel
- Fork this repository
- Import to Vercel
- Add environment variables:
NEXTAUTH_SECRET=your-random-secret NEXTAUTH_URL=https://your-app.vercel.app GOOGLE_CLIENT_ID=your-google-client-id GOOGLE_CLIENT_SECRET=your-google-client-secret DATABASE_URL=your-postgresql-url REDIS_URL=your-redis-url - Deploy
5. Initialize Database
After deployment, run database migrations:
pnpm db:push
Usage
Simple Setup (OAuth-on-Demand)
- Add MCP server to Claude Desktop (no setup required):
claude mcp add --transport sse google-docs https://your-app.vercel.app/sse
Or manually add to claude_desktop_config.json:
{
"mcpServers": {
"google-docs": {
"command": "claude",
"args": ["mcp", "connect", "sse", "https://your-app.vercel.app/sse"]
}
}
}
-
First-time authorization:
- In Claude Desktop, run: "Use the authorize_google tool"
- Claude will provide an authorization link
- Click the link → browser opens → sign in with Google
- After authorization, all Google Docs tools work automatically
-
Available Tools:
authorize_google- Authorize Google Docs access (run this first)read_document- Read content from Google Docscreate_document- Create new Google Docsupdate_document- Update document content with batch operationsappend_text- Append text to documentslist_documents- List your Google Docs
Alternative: API Key Setup (Advanced)
For programmatic access or multiple clients:
-
Web Setup:
- Visit your deployed app:
https://your-app.vercel.app - Sign in with Google
- Create an API key
- Visit your deployed app:
-
Claude Desktop Setup:
claude mcp add --transport sse google-docs \\
https://your-app.vercel.app/sse \\
--header "X-API-Key: your-api-key"
Development
Local Setup
- Clone the repository
- Install dependencies:
pnpm install - Copy
.env.exampleto.envand fill in values - Run database migrations:
pnpm db:push - Start development server:
pnpm dev
Commands
pnpm dev- Start development serverpnpm build- Build for productionpnpm start- Start production serverpnpm lint- Run ESLintpnpm db:generate- Generate database migrationspnpm db:push- Push schema to databasepnpm db:studio- Open Drizzle Studio
Security
- API keys are hashed before storage
- Google refresh tokens are encrypted in database
- User isolation prevents cross-user access
- HTTPS enforced for OAuth callbacks
Troubleshooting
Common Issues
- OAuth Error: Check redirect URI matches exactly
- Database Connection: Verify DATABASE_URL format
- API Key Invalid: Ensure X-API-Key header is set correctly
- Redis Connection: Verify REDIS_URL for SSE transport
Logs
Check Vercel function logs for detailed error information.
Contributing
- Fork the repository
- Create a feature branch
- Make changes
- Test locally
- Submit a pull request
License
MIT License - see LICENSE file for details.
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.