Google Workspace MCP Server
@taylorwilsdon
About Google Workspace MCP Server
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace / G Suite MCP Server & CLI Tool
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"google_workspace_mcp": {
"command": "uvx",
"args": [
"workspace-mcp",
"--tool-tier",
"core",
"#",
"essential",
"tools"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Google Workspace MCP Server?
Google Workspace MCP Server provides full natural language control over Google Calendar, Drive, Gmail, Docs, Sheets, Slides, Forms, Chat, Apps Script, Tasks, Contacts, and Search through any MCP client, AI assistant, or developer tool. It includes a CLI and Code Mode for tools like Claude Code.
How to use Google Workspace MCP Server?
Set up OAuth credentials in Google Cloud, export GOOGLE_OAUTH_CLIENT_ID and optionally GOOGLE_OAUTH_CLIENT_SECRET, then launch with uvx workspace-mcp choosing a tool tier (core, extended, complete) and transport (stdio or streamable-http). Connect the server to any MCP client such as Claude Desktop, VS Code, or LM Studio.
Key features of Google Workspace MCP Server
- Integrates 12 Google Workspace services in one MCP server
- Supports OAuth 2.0 and OAuth 2.1 with PKCE
- Offers three tool tiers: core, extended, complete
- Operates in stateless mode for containerized environments
- Uses your own OAuth client and GCP project; no third‑party services
- Fully open source under MIT license; no telemetry or analytics
Use cases of Google Workspace MCP Server
- Automate cross‑service workflows (e.g., create a Doc from Gmail attachments)
- Manage an organization’s Google Workspace via a centrally hosted MCP instance
- Build AI‑powered assistants that can read, edit, and send emails, files, and calendar events
- Deploy in locked‑down environments using stateless mode and a reverse proxy
FAQ from Google Workspace MCP Server
What are the runtime requirements?
Python 3.10 or higher. Requires a Google Cloud project with OAuth 2.0 credentials and at least one consent screen scope.
Does this server send data anywhere besides Google APIs?
No. The server never contacts any endpoint you didn’t configure. There is no telemetry, usage reporting, analytics, or SaaS dependency. All data flows from your infrastructure to Google’s APIs.
How does authentication work?
You provide your own OAuth client ID (and secret for confidential clients). The server supports OAuth 2.0, OAuth 2.1 with PKCE, multi‑user bearer tokens, and external OAuth provider mode. Tokens are stored locally and auto‑refreshed.
Can I host this server for my entire organization?
Yes. It supports stateless mode, reverse proxy setups, and external OAuth 2.1 provider mode, allowing centralized, secure hosting with multi‑user authentication.
What transports are supported?
Two transports: stdio (default for local CLI use) and streamable‑HTTP (required for OAuth 2.1 and remote connections). The transport can be set via the --transport flag or WORKSPACE_MCP_TRANSPORT environment variable.
Frequently asked questions
What are the runtime requirements?
Python 3.10 or higher. Requires a Google Cloud project with OAuth 2.0 credentials and at least one consent screen scope.
Does this server send data anywhere besides Google APIs?
No. The server never contacts any endpoint you didn’t configure. There is no telemetry, usage reporting, analytics, or SaaS dependency. All data flows from your infrastructure to Google’s APIs.
How does authentication work?
You provide your own OAuth client ID (and secret for confidential clients). The server supports OAuth 2.0, OAuth 2.1 with PKCE, multi‑user bearer tokens, and external OAuth provider mode. Tokens are stored locally and auto‑refreshed.
Can I host this server for my entire organization?
Yes. It supports stateless mode, reverse proxy setups, and external OAuth 2.1 provider mode, allowing centralized, secure hosting with multi‑user authentication.
What transports are supported?
Two transports: stdio (default for local CLI use) and streamable‑HTTP (required for OAuth 2.1 and remote connections). The transport can be set via the `--transport` flag or `WORKSPACE_MCP_TRANSPORT` environment variable.
Basic information
More Other MCP servers

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
ghidraMCP
LaurieWiredMCP Server for Ghidra
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
Comments