Home/AI Agents/google_workspace_mcp
google_workspace_mcp logo

google_workspace_mcp

taylorwilsdon/google_workspace_mcp

Control Google Workspace apps via AI MCP server and CLI tool

GraphCanon updated 3w · GitHub synced 3w · 31 views this month

2.9k stars901 forksLast push 3w Python MIT

Decision brief

AI-driven server and CLI for interactive Google Workspace control using MCP

Good fit when

  • You need AI-powered automation across multiple Google Workspace apps like Gmail, Calendar, Docs, Sheets
  • Your project requires Model Context Protocol (MCP) integration specifically

Avoid when

  • If your project focuses solely on a single app or does not benefit from broader automated control over multiple services
  • For scenarios where MCP compatibility is not necessary and simpler direct API access suffices

Observed Jul 16, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Very active (0d since push)
As of 3w
Provenance
Not a fork · Personal account
As of 3w
Security (OSV)
No MCP manifest
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install google_workspace_mcp
PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

This repository provides an AI-driven control suite for Google's Workspace applications such as Gmail, Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search, and Drive. It employs the Model Context Protocol (MCP) for facilitating interactions.

Capability facts

Deploy
Self-host

Source: dockerfile:Dockerfile · Jul 26, 2026

Docker
Dockerfile present

Source: dockerfile:Dockerfile · Jul 26, 2026

CLI
CLI entrypoint

Source: pyproject.toml:[project.scripts] · Jul 26, 2026

MCP server
No MCP server detected

Source: repo_scan · Jul 26, 2026

Languages
python

Source: github.language+pyproject.toml · Jul 26, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Jul 26, 2026)

"command": "npx",
Source link
Works with Claude DesktopClaude Desktop

Source: README excerpt (regex_v1, Jul 26, 2026)

If you need to use HTTP mode with Claude Desktop:
Source link

Tags

README

Quick Start

Set credentials → pick a launch command → connect your client

💡 New to Workspace MCP? Check out the Interactive Quick Start Guide → with step-by-step setup, screenshots, and troubleshooting tips!

Confidential Client Quick Start


---

### Quick Start — Connect Claude to Google Workspace

The recommended setup is to run an instance and connect Claude to it via a **Connector**. Full instructions at **[workspacemcp.com/quick-start](https://workspacemcp.com/quick-start)**.

<div align="center">
  <video width="832" src="https://github.com/user-attachments/assets/83cca4b3-5e94-448b-acb3-6e3a27341d3a"></video>
</div>

---

---

### 2. Advanced / Cross-Platform Installation

If you’re developing, deploying to servers, or using another MCP-capable client, keep reading.

#### Instant CLI (uvx)

<details open>
<summary>⚡ <b>Quick Start with uvx</b> <sub><sup>← No installation required!</sup></sub></summary>

```bash

---

# Install everything needed for linting, tests, and release tooling
uv sync --group dev

---

# Public deployment — restrict to Claude's hosted OAuth callbacks
export WORKSPACE_MCP_ALLOWED_CLIENT_REDIRECT_URIS="https://claude.ai/api/mcp/auth_callback,https://claude.com/api/mcp/auth_callback"

---

# Optional: install the bundled Claude skill for better Workspace tool routing
mkdir -p ~/.claude/skills
ln -s "$(pwd)/skills/managing-google-workspace" ~/.claude/skills/managing-google-workspace

Or copy skills/managing-google-workspace into ~/.claude/skills/managing-google-workspace if you prefer not to symlink it.

Reverse Proxy Setup

If you're running the MCP server behind a reverse proxy (nginx, Apache, Cloudflare, etc.), you have two configuration options:

Problem: When behind a reverse proxy, the server constructs OAuth URLs using internal ports (e.g., http://localhost:8000) but external clients need the public URL (e.g., https://your-domain.com).

Solution 1: Set WORKSPACE_EXTERNAL_URL for all OAuth endpoints:


---

### Development Installation

For development or customization:

```bash
git clone https://github.com/taylorwilsdon/google_workspace_mcp.git
cd google_workspace_mcp
uv run main.py

Development Installation (For Contributors):

🔧 Developer Setup JSON ← For contributors & customization
{
  "mcpServers": {
    "google_workspace": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/repo/google_workspace_mcp",
        "main.py"
      ],
      "env": {
        "GOOGLE_OAUTH_CLIENT_ID": "your-client-id",
        "GOOGLE_OAUTH_CLIENT_SECRET": "your-secret",
        "OAUTHLIB_INSECURE_TRANSPORT": "1"
      }
    }
  }
}

HTTP Mode (For debugging or web interfaces)

If you need to use HTTP mode with Claude Desktop:

{
  "mcpServers": {
    "google_workspace": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:8000/mcp"]
    }
  }
}

Note: Make sure to start the server with --transport streamable-http when using HTTP mode. For remote or shared HTTP endpoints, also enable OAuth 2.1 with MCP_ENABLE_OAUTH21=true and GOOGLE_OAUTH_CLIENT_ID.


Install the optional dependency if you plan to use the GCS backend:


≡ License

MIT License - see LICENSE file for details.


Validations:

Batch Emails

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.