AI Agents
lamda
FIRERPA / LAMDA — full-stack Android device control: remote desktop, automation, MITM, Frida and MCP.
★ 8.6k starsMIT
View guide →// agents · taylorwilsdon/google_workspace_mcp
google_workspace_mcp
google_workspace_mcp is an open-source ai agents project by taylorwilsdon (taylorwilsdon/google_workspace_mcp on GitHub). It has 3,305 GitHub stars and 1,036 forks, is released under the MIT license, and was last updated on GitHub on 7 October 2026.
Control Gmail, Calendar, Docs, Sheets, Drive and more from AI — a full Google Workspace MCP server.
★ 3.3k stars⑂ 1.0k forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- taylorwilsdon/google_workspace_mcp
- GitHub stars
- 3,305
- Forks
- 1,036
- License
- MIT
- Last updated on GitHub
- 7 October 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Clarify your goal
Decide the first concrete outcome you want from it, so you can pick the right example, template or mode instead of exploring everything at once.
- Get the project
Clone the repository (or install the published package) and skim its README quick start for the requirements for your platform.
- Install and configure
Run the documented install step and set any required configuration — such as provider keys, data sources or local services — before the first run.
- Run your first task
Execute the smallest documented example end to end, confirm the output is what you expected, then adapt it to your real data or workflow.
// features
Why people love it
Every major Workspace service
Gmail, Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search and Drive in one server.
Tiered tool sets
Launch with --tool-tier core, extended or complete, or cherry-pick services to limit exposure.
Your credentials, your project
Your OAuth client and GCP project; credentials never leave your environment, with sensitive-path blocking for local files.
Serious deployment options
OAuth 2.1 multi-user auth, stateless container mode, external OAuth providers, trusted-gateway identity and OpenTelemetry tracing.
CLI included
workspace-cli lists and calls tools directly, e.g. searching Gmail from the terminal.
Security-first docs
Documented best practices for prompt injection, secret handling and production HTTPS setups.
Advertisement
// run it
Run it yourself
- Clone the repository
Get the source so you can inspect, configure and run it locally.
git clone https://github.com/taylorwilsdon/google_workspace_mcp.git cd google_workspace_mcp - Create Google OAuth credentials
In Google Cloud, create an OAuth client, then export its ID and secret (or point GOOGLE_CLIENT_SECRET_PATH at client_secret.json).
export GOOGLE_OAUTH_CLIENT_ID="..." export GOOGLE_OAUTH_CLIENT_SECRET="..." - Launch the server
Start with the core tier via uvx, or HTTP mode for shared deployments, then connect your MCP client.
uvx workspace-mcp --tool-tier core # HTTP mode for clients: claude mcp add --transport http workspace-mcp http://localhost:8000/mcp
// use cases
What you can build
- Have Claude triage your Gmail and draft replies every morning
- Let an agent schedule meetings and update a project Sheet
- Give a whole team Workspace access through one OAuth 2.1 HTTP server
- Search Drive and summarise a Doc from the terminal via workspace-cli
Advertisement
// faq
Questions, answered
Who maintains google_workspace_mcp?
It is maintained by taylorwilsdon on GitHub (taylorwilsdon/google_workspace_mcp), where the source, issues and releases live.
Is it free to use?
Yes — it is free and open source under the MIT licence, which permits use, modification and redistribution, including commercially, with attribution.
Does it need a paid API key?
No Google API key billing for standard Workspace APIs, but you must create a free Google Cloud OAuth client; your AI client uses its own model access.
How does it compare to Google's own Workspace integrations inside Gemini alone?
Compared with Google's own Workspace integrations inside Gemini alone, google_workspace_mcp's distinguishing focus is: control Gmail, Calendar, Docs, Sheets, Drive and more from AI — a full Google Workspace MCP server. Pick it when that focus matches your need; the alternative may suit you better if its broader or different scope is the priority.
How do I get started?
Clone https://github.com/taylorwilsdon/google_workspace_mcp (or install its published package), follow the README quick start to install and configure it, then run the smallest documented example — the Run section on this page mirrors those steps.
// keep exploring
Similar tools
AI Agents
dbhub
A token-conscious MCP server that connects AI tools to Postgres, MySQL, SQLite and more.
★ 3.6k starsMIT
View guide →AI Agents
ha-mcp
The unofficial Home Assistant MCP server — control and automate your smart home from any AI assistant.
★ 5.0k starsMIT
View guide →AI Agents
ghidra-mcp
Ghidra MCP server with 200+ tools that let AI assistants drive real reverse-engineering work
★ 4.9k starsApache-2.0
View guide →AI Agents
x64dbg-mcp-server
Native MCP plugin for x64dbg — let an AI drive the debugger: breakpoints, stepping, memory, registers
★ 2.4k starsMIT
View guide →AI Agents
AppFlowy
Bring projects, wikis, and teams together with AI. AppFlowy is the AI collaborative workspace where you achieve more without losing control of your data. The…
★ 77.1k starsAGPL-3.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if google_workspace_mcp is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to google_workspace_mcp — keep exploring the shelf either side of it.
- EvoAgentX★ 3.4k
EvoAgentX — a framework for building self-evolving ecosystems of AI agents.
- mobile-use★ 3.2k
AI agents that use real Android and iOS apps like a human — from minitap.
- beeai-framework★ 3.4k
Build production-ready AI agents in both Python and Typescript.
- AP2★ 3.2k
An open protocol for secure AI-driven payments.
- obsidian-wiki★ 3.5k
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
- arxiv-mcp-server★ 3.2k
A local MCP server for serious arXiv work — LaTeX section reads, BibTeX and topic watches.
Get google_workspace_mcp
Free and open — grab the source, star the repo, and start creating.