Google Workspace MCP Server

Google Workspace MCP Server

Enables Claude Code to interact with Google Workspace services (Drive, Docs, Sheets, Slides, Forms, Gmail) via OAuth 2.0 authentication and natural language commands.

Category
Visit Server

README

Google Workspace MCP Server

A Model Context Protocol server for seamless integration between Claude Code and Google Workspace services.

Features

āœ… Complete Google Workspace Integration

  • Google Drive: Full file management (search, read, create, update, delete, upload/download)
  • Google Docs: Document creation, reading, and editing
  • Google Sheets: Spreadsheet operations with range updates and batch processing
  • Google Slides: Presentation management and slide manipulation
  • Google Forms: Form creation, editing, and response collection
  • Gmail: Email search, read, send, reply, and label management

šŸ”’ Secure Authentication

  • OAuth 2.0 authentication with automatic token refresh
  • Encrypted token storage
  • Minimal scope requirements

⚔ Performance Optimized

  • Async/await architecture for concurrent operations
  • Built-in caching with TTL
  • Smart rate limiting to prevent API quota exhaustion
  • Request batching where possible

šŸ›”ļø Robust Error Handling

  • Comprehensive error management
  • Automatic retry logic for transient failures
  • Detailed error messages for debugging

Installation

Prerequisites

  • Python 3.10 or higher
  • Google Cloud Project with Workspace APIs enabled
  • OAuth 2.0 credentials

Step 1: Clone and Setup

# Clone the repository
git clone https://github.com/YOUR_USERNAME/google-workspace-mcp.git
cd google-workspace-mcp

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt
pip install -e .

# Create config directory
mkdir -p config

Step 2: Google Cloud Console Setup

  1. Go to Google Cloud Console

  2. Create a new project or select existing one

  3. Enable the following APIs:

    • Google Drive API
    • Google Docs API
    • Google Sheets API
    • Google Slides API
    • Google Forms API
    • Gmail API
  4. Configure OAuth Consent Screen:

    • Go to "APIs & Services" > "OAuth consent screen"
    • Choose "External" user type
    • Fill in required fields (App name, User support email, Developer contact)
    • Add scopes:
      • https://www.googleapis.com/auth/drive
      • https://www.googleapis.com/auth/documents
      • https://www.googleapis.com/auth/spreadsheets
      • https://www.googleapis.com/auth/presentations
      • https://www.googleapis.com/auth/forms
      • https://www.googleapis.com/auth/gmail.modify
  5. Create OAuth 2.0 Client ID:

    • Go to "Credentials" > "Create Credentials" > "OAuth client ID"
    • Choose "Desktop app" as application type
    • Download credentials JSON file
    • Copy config/credentials.json.example to config/credentials.json
    • Replace the example values with your downloaded credentials

Step 3: Initial Authentication

# Run server for first-time authentication
python3 -m google_workspace_mcp

# Browser will open for OAuth consent
# Grant necessary permissions
# Token will be saved automatically

Step 4: Claude Code Integration

Add to your Claude Code MCP settings (~/.claude/config/settings.json):

{
  "mcpServers": {
    "google-workspace": {
      "command": "/usr/local/bin/python3",
      "args": ["-m", "google_workspace_mcp"],
      "cwd": "/path/to/your/google-workspace-mcp",
      "env": {}
    }
  }
}

Note: Replace /path/to/your/google-workspace-mcp with your actual installation path.

Available Tools

Google Drive (8 tools)

  • drive_search_files - Search files/folders
  • drive_read_file - Read file content
  • drive_create_file - Create new file
  • drive_update_file - Update existing file
  • drive_delete_file - Delete file
  • drive_upload_file - Upload local file
  • drive_download_file - Download to local
  • drive_list_shared_drives - List Team Drives

Google Docs (4 tools)

  • docs_create - Create document
  • docs_read - Read document
  • docs_update - Update document
  • docs_delete - Delete document

Google Sheets (4 tools)

  • sheets_create - Create spreadsheet
  • sheets_read - Read range
  • sheets_update - Update range
  • sheets_delete - Delete spreadsheet

Google Slides (4 tools)

  • slides_create - Create presentation
  • slides_read - Read presentation
  • slides_update - Update slides
  • slides_delete - Delete presentation

Google Forms (5 tools)

  • forms_create - Create form
  • forms_read - Read form structure
  • forms_update - Update form
  • forms_delete - Delete form
  • forms_get_responses - Get form responses

Gmail (6 tools)

  • gmail_search_messages - Search emails
  • gmail_read_message - Read email content
  • gmail_send_message - Send new email
  • gmail_reply_message - Reply to email
  • gmail_delete_message - Delete email
  • gmail_list_labels - List labels

Usage Examples

Search Drive Files

In Claude Code:
"Search my Drive for files named 'project report'"

Uses: drive_search_files with query parameter

Read and Summarize Document

"Read the document with ID xyz and summarize it"

Uses: drive_read_file → Processes content

Send Email

"Send an email to team@example.com with subject 'Meeting Update' and body '...'"

Uses: gmail_send_message

Create Spreadsheet

"Create a new spreadsheet called 'Q4 Budget' with headers A1:E1"

Uses: sheets_create → sheets_update

Configuration

Environment Variables

# Optional: Custom config directory
export GW_MCP_CONFIG_DIR=~/.config/gw-mcp

# Optional: Log level
export GW_MCP_LOG_LEVEL=INFO  # DEBUG, INFO, WARNING, ERROR

Cache Settings

Default cache TTL: 300 seconds (5 minutes) Max cache size: 1000 items

Rate Limiting

Default limits:

  • 100 requests per 60 seconds per service
  • Burst limit: 10 consecutive requests

Troubleshooting

Authentication Issues

# Clear stored tokens
rm ~/.config/gw-mcp/token.pickle

# Re-authenticate
python3 -m google_workspace_mcp

Permission Errors

  • Verify all required APIs are enabled in Google Cloud Console
  • Check OAuth scopes in consent screen configuration
  • Ensure credentials.json is in correct location

Rate Limit Errors

  • Server automatically handles rate limiting with exponential backoff
  • Check Google Cloud Console quotas if persistent issues

Import Errors

# Reinstall dependencies
pip install -r requirements.txt --force-reinstall

Development

Running Tests

pytest tests/
pytest tests/ --cov=src --cov-report=html

Project Structure

google-workspace-mcp/
ā”œā”€ā”€ src/
│   ā”œā”€ā”€ auth/           # OAuth authentication
│   ā”œā”€ā”€ services/       # Google API wrappers
│   ā”œā”€ā”€ tools/          # MCP tool definitions
│   ā”œā”€ā”€ utils/          # Utilities (logging, caching, etc.)
│   └── server.py       # Main MCP server
ā”œā”€ā”€ config/             # Configuration files
ā”œā”€ā”€ tests/              # Test suite
ā”œā”€ā”€ requirements.txt    # Dependencies
ā”œā”€ā”€ setup.py           # Package setup
└── README.md          # This file

Architecture

Claude Code (MCP Client)
        ↓
MCP Protocol (stdio)
        ↓
Google Workspace MCP Server
  ā”œā”€ā”€ MCP Handler (Tool Registry)
  ā”œā”€ā”€ Service Layer (API Wrappers)
  │   ā”œā”€ā”€ Drive Service
  │   ā”œā”€ā”€ Docs Service
  │   ā”œā”€ā”€ Sheets Service
  │   ā”œā”€ā”€ Slides Service
  │   ā”œā”€ā”€ Forms Service
  │   └── Gmail Service
  ā”œā”€ā”€ Auth Manager (OAuth 2.0)
  └── Infrastructure (Cache, Rate Limit, Logging)
        ↓
Google Workspace APIs

Security Considerations

  • Token Storage: Tokens encrypted and stored securely in user config directory
  • Scope Minimization: Only requests necessary permissions
  • No Credential Logging: Sensitive data never logged
  • Automatic Token Refresh: Expired tokens refreshed automatically
  • Rate Limiting: Prevents quota exhaustion and API abuse

Contributing

Contributions welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Add tests for new functionality
  4. Submit a pull request

License

MIT License - see LICENSE file for details

Support

For issues and questions:

  • Open an issue on GitHub
  • Check troubleshooting section
  • Review Google Workspace API documentation

Acknowledgments

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured