Your AI can read your email, check your calendar, manage your contacts, and track your tasks — but only if it can talk to Google. GSuite MCP is the bridge. It runs locally as an MCP server and gives any MCP-compatible client access to four Google APIs through 33 tools.

Install

brew install 2389-research/tap/gsuite-mcp

Or build from source:

go build ./cmd/gsuite-mcp

What it does

Gmail — read, search, send, draft, label, trash, and delete messages. CC/BCC supported.

Calendar — list, view, create, update, and delete events.

Contacts — search, browse, create, update, and delete via the People API.

Tasks — manage task lists and individual tasks: create, update, complete, delete.

Beyond the tools, the server ships with prompts for common workflows: triaging your inbox, composing threaded replies, scheduling around your availability, reviewing pending tasks, and looking up contacts. It also exposes live MCP resources — today’s calendar, unread mail, overdue tasks — so your AI has context before you ask.

Multi-account support is built in. Connect your work and personal Google accounts, then tell your AI which one to use:

“Check my work email for anything urgent” “What’s on my personal calendar this week?”

How it works

GSuite MCP runs as a local process. You authenticate once with gsuite-mcp setup, which opens a browser for Google OAuth. Tokens stay on your machine in ~/.local/share/gsuite-mcp/ — nothing leaves your computer. The server requests only the OAuth scopes it needs.

Add it to Claude Code with one command:

claude mcp add gsuite gsuite-mcp -- mcp

Or drop the config into any MCP-compatible client.

Requirements

Google Cloud project with OAuth credentials (credentials.json)
Gmail, Calendar, People, and Tasks APIs enabled on that project
Go 1.21+ (only if building from source)