google-workspace-mcp: Instructions file for Claude Code

CLAUDE.md

google-workspace-mcp CLAUDE.md is an instructions file for Claude Code from tom275275/google-workspace-mcp. It costs 2,472 tokens per session, scanned C, original, MIT.

Project instructions for deploying and connecting a Google Workspace MCP server, a service that lets AI tools work with Google Workspace through a standard connection.

In plain words
What is it for?
Use it when deploying this Google Workspace service on Google Cloud Run or registering its remote endpoint in Claude Code or Claude.ai.
Why use it?
It records the live service addresses, deployment details, version, and the correct Claude Code setup, reducing configuration mistakes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is tom275275/google-workspace-mcp's own configuration. It tells Claude Code how to work on google-workspace-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything google-workspace-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/tom-unix/projects/google-workspace-mcp.

Reuse

Borrowing it

Nothing to install: this file belongs to tom275275/google-workspace-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tom275275/google-workspace-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tom275275/google-workspace-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for google-workspace-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tom275275/google-workspace-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/tom275275/google-workspace-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tom275275/google-workspace-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tom275275/google-workspace-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for google-workspace-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tom275275/google-workspace-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tom275275/google-workspace-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,472 This file is loaded in full into every session.
When invoked 2,472 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02472 $0.02472
Opus 5 $0.01236 $0.01236
Sonnet 5 $0.00494 $0.00494
Haiku 4.5 $0.00247 $0.00247

Measured 9d ago against content hash c18bc6da97dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

google-workspace-mcp CLAUDE.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt install xdg-utils

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

Don't blindly enable all tools. Claude Code already has first-party integrations for Gmail
CLAUDE.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Workspace MCP — Cloud Run Deployment

Overview

This is a fork of taylorwilsdon/google_workspace_mcp, deployed as a remote MCP server on Google Cloud Run for personal use by [email protected].

Local changes from upstream are limited to: CLAUDE.md, cloudbuild.yaml, README.md, and the icon addition in core/server.py.

Live Service

MCP Client Configuration

Claude Code

Register via CLI (user scope, persists across projects):

claude mcp add --transport http --scope user google-workspace https://google-workspace-mcp-557522843498.us-central1.run.app/mcp

This writes to ~/.claude.json — the correct location for user-scoped MCP servers.

Note: ~/.claude/mcp.json does NOT work for registering MCP servers in Claude Code. Always use claude mcp add or edit ~/.claude.json directly.

Claude.ai

Add via Settings → Integrations → Add custom integration, using the MCP endpoint URL above. First use will trigger a Google OAuth consent flow in the browser.

Architecture

  • Runtime: Python 3.11 on Cloud Run (managed, serverless)
  • Transport: streamable-http (MCP over HTTP, suitable for remote clients)
  • Auth: OAuth 2.1 with Web application OAuth client
  • Secrets: Stored in Google Secret Manager, mounted as env vars at runtime
  • Scaling: Scales to zero when idle; cold start ~2-3s
  • CI/CD: Cloud Build trigger on push to main auto-deploys

Enabled Tools

Gmail and Calendar are intentionally disabled — deferred to claude.ai's first-party integrations. Chat and Slides are also disabled (not needed).

Read the full file on GitHub · 215 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 215 lines · 2,472 tokens per session scan C c18bc6da97dc

Subscribe to this mod's changes

google-workspace-mcp CLAUDE.md is an instructions file published in the GitHub repository tom275275/google-workspace-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 2,472 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories