taylorwilsdon/google_workspace_mcp

What it solves

This project provides a comprehensive Model Context Protocol (MCP) server that allows AI assistants to interact with the full suite of Google Workspace services. It solves the problem of fragmented or limited AI integrations with Google's ecosystem, offering a single, secure interface for AI agents to read, write, and manage data across Gmail, Drive, Calendar, and other Workspace apps.

How it works

The server acts as a bridge between MCP-compliant AI clients (like Claude Desktop, Claude Code, or ChatGPT) and Google's APIs. It leverages OAuth 2.1 for secure authentication and can be deployed locally via stdio or remotely via streamable HTTP. It organizes its 120+ available tools into three tiers (core, extended, and complete) to prevent overloading the AI's context window.

Who it’s for

• AI Developers: Those building agents that need deep integration with Google Workspace.
• Enterprise Teams: Organizations wanting to host a central, secure MCP server for their entire team using native OAuth and stateless container deployments.
• End Users: Individuals using AI assistants to automate their personal productivity tools.

Highlights

• Extensive Coverage: Supports 12 major services including Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Custom Search, and Apps Script.
• Enterprise-Ready: Features multi-user OAuth 2.1 support, stateless deployment for locked-down containers, and trusted-gateway identity integration.
• Flexible Deployment: Supports both local stdio and remote HTTP transport.
• Granular Control: Offers tool tiers, read-only mode, and the ability to cherry-pick specific services or disable individual tools.