About Google Workspace (multi-account)
Google Workspace (multi-account) is a local MCP server for people using Google Workspace through AI clients. It exposes OAuth-reachable API methods across multiple accounts, with discover-first access and writes denied by default.
Key features
- 01Tools spanning 29 Workspace services
- 02Operate across multiple accounts
- 03Discover-first tool workflow
- 04Writes denied by default
- 05Local stdio or self-hosted HTTP
Use cases
- 01Search or reply to Gmail across accounts
- 02Work with Drive, Calendar, or Sheets data
- 03Use Workspace APIs from an MCP client
MCP support
It exposes Google Workspace API methods as MCP tools for MCP clients. It runs locally over stdio or as a self-hosted HTTP server with a built-in OAuth 2.1 server.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-google-multi
The most complete local Google Workspace MCP server: Gmail, Drive, Calendar, Sheets, Docs, Slides, Forms, Contacts, Tasks, Chat, Meet, Analytics (GA4), Search Console, Classroom, Vault, Admin and more — every OAuth-reachable API method as a tool, across multiple Google accounts at once, from Claude Code or any MCP client.
- 🧰 Exhaustive — 942 tools across 29 services, now including Google Analytics (GA4), + an escape hatch for anything else → COVERAGE.md
- 🔑 Multi-account — drive any number of Google accounts by alias, or fan one call out across all of them
- 🔒 Private by design — your own OAuth app, tokens encrypted at rest (AES-256-GCM), writes deny-by-default, no telemetry, no metering — it talks only to Google
- 🌐 Local or remote — runs locally over stdio, or self-hosted over HTTP with its own built-in OAuth 2.1 server (Claude Code's
/mcplogin and the claude.ai connector, zero custom UI). Pull-and-up Docker Compose with optional automatic HTTPS → remote setup - ✉️ Built for real work — send and read email in Markdown with attachments and one-call replies, an interactive setup wizard with a
doctorself-check, and per-account scope profiles → features tour
Quick setup
New to all this? It's written for someone who just installed Claude Code and has never made an API key. Copy-paste each step; it says what you'll see. (Already technical? The Configuration reference is the terse version.)
-
Install it. Get Node.js (the green "LTS" button, version 22 or newer), then run:
npm install -g mcp-google-multiClaude Desktop user? You can skip npm entirely: download the
mcp-google-multi.mcpbbundle from the latest release, double-click it (or drag it into Claude Desktop → Settings → Extensions), and fill in the values from step 2 when prompted. -
Make your Google key (the one manual part, a few minutes, because Google has no way to script it). Follow the step-by-step Google Cloud setup, or just ask Claude Code: "walk me through creating a Google OAuth Desktop client for mcp-google-multi." You finish with two values, a Client ID and a Client Secret. It's free and private to you.
-
Put them in a file. In the folder you'll run from, make a file named
.envand paste this, filling in your values:GOOGLE_CLIENT_ID=paste-your-client-id GOOGLE_CLIENT_SECRET=paste-your-client-secret # any short nickname, then your Gmail address: GOOGLE_ACCOUNTS=me:[email protected]No encryption key to make: the server generates and stores one for you.
-
Sign in. A browser opens; pick your account and click Allow:
mcp-google-multi auth --account me -
Add it to Claude Code, then restart Claude Code:
claude mcp add mcp-google-multi -s user -- npx -y mcp-google-multi
Stuck at any point? Run mcp-google-multi doctor. It inspects every part and prints the exact fix for anything wrong (a missing sign-in, a Google API you still need to switch on, and so on). Once it reads all-green, just talk to Claude: "summarize my unread email."
Got more than one Google account? Add them together, like GOOGLE_ACCOUNTS=me:[email protected],work:[email protected], and run step 4 once per nickname.
On a server or from claude.ai? Advanced path: Remote / HTTP setup. Coming from v5? v6 migration guide.
Go deeper: Configuration reference · What's covered · Features tour · Remote / HTTP setup · Secrets in a vault · Local usage metrics · Migrating to v6 · Security policy · Roadmap
Agent skill
The repo and the npm package both ship an Agent Skill at skills/google-workspace/: a hand-written SKILL.md covering account selection, the discover step, incremental Gmail sweeps, keeping results small, write profiles, and the escape hatch, plus a reference/ folder with a generated argument table per service. Loading it gets an agent calling this server's tools correctly without guessing argument names.
To install it for Claude Code, copy or symlink the skills/google-workspace folder into ~/.claude/skills/ (every project) or a project's own .claude/skills/ (that project only):
# from a cloned copy of this repo
ln -s "$(pwd)/skills/google-workspace" ~/.claude/skills/google-workspace
# from the installed npm package
ln -s "$(npm root -g)/mcp-google-multi/skills/google-workspace" ~/.claude/skills/google-workspace
Maintainer, sponsor & license
Built and maintained by Abdelbaki Berkati — berkati.xyz · @bakissation. Read the case study →
Development is funded by IdeaCrafters (@IdeaCraftersHQ) — the studio that pays for this OSS to exist.
An Enterprise Edition (hosted, multi-tenant) is available: ask through berkati.xyz (email or LinkedIn there).
Thanks to contributors @obatried, @trevor-commits, and @mjreddy. The project is maintainer-led (roadmap on Milestones; bug reports welcome, feature PRs by prior agreement — see CONTRIBUTING.md). Feedback shapes the roadmap: open an issue with bugs, pain points, or what you wish it did. Security reports go to SECURITY.md, never a public issue.
Licensed under MIT.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.