Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/rajool/google-workspace-mcp/google-workspace-setupgit clone --depth 1 https://github.com/rajool/google-workspace-mcpWrote 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.
[](https://agentmods.dev/commands/rajool/google-workspace-mcp/google-workspace-setup)<a href="https://agentmods.dev/commands/rajool/google-workspace-mcp/google-workspace-setup"><img src="https://agentmods.dev/badge/commands/rajool/google-workspace-mcp/google-workspace-setup.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.00707 |
| Opus 5 | $0.00020 | $0.00353 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
google-workspace-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace MCP — setup
Guide the user through standing up the multi-account Google Workspace MCP server. Be concise; do the mechanical steps yourself. Never ask the user to paste secrets into chat — only to place files or click Allow.
1. Prerequisites
uv --version— if missing, point to https://docs.astral.sh/uv/ and stop.- OAuth client secret at
~/.config/google-workspace-mcp/credentials.json(honor$GWM_HOME/$GWM_CREDENTIALS/$XDG_CONFIG_HOME). If missing, walk them through Google Cloud Console (own project; enable Gmail, Calendar, Drive APIs; OAuth consent screen External + add their accounts as test users; create an OAuth client → Desktop app; download and save to that path). - Server binary on PATH:
google-workspace-mcp --help. If missing:uv tool install git+https://github.com/rajool/google-workspace-mcp(oruv tool install .from a local clone).
2. Define accounts
Pick a short slug per account. Either create
~/.config/google-workspace-mcp/accounts.json (see accounts.example.json
in the repo) or plan to pass them inline via GWM_ACCOUNTS.
3. Authorize each account
The authorize CLI prints a Google consent URL and waits on a localhost redirect. The key rule: open the URL in a browser signed into the account being authorized.
For each account:
- Run in the background:
google-workspace-authorize <slug>(account already in the registry), orgoogle-workspace-authorize <slug> <email> "<Display Name>"to register a new one. It printsAUTH_URL: <url>. - If the Claude in Chrome extension is connected, call
list_connected_browsers, pick the browser whose name matches that account's email,select_browserit,navigateto the AUTH_URL, and click through the unverified-app warning → Continue → Select all → Continue. Otherwise hand the user the URL for the right browser/profile. - The CLI writes
~/.config/google-workspace-mcp/tokens/<slug>.json.
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.
- 4d ago First seen · 68 lines · 41 tokens per session scan A a524a773f005
google-workspace-setup is a command published in the GitHub repository rajool/google-workspace-mcp (2 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
draft-email
Draft a Gmail email or reply in your voice with full CRM/knowledge-base context loaded and every claim verified. Always creates a draft — never sends.
prep-meeting
Pre-meeting brief — looks up attendees in CRM, reads recent transcripts, and Slack-DMs you 3-5 main points before a meeting. Not a full page — just what you need to walk in informed.
gw-inbox
Quick inbox scan — shows recent emails.
gw-setup
First-run setup for the Google Workspace plugin — creates the venv, walks you through a Google Cloud OAuth client, and authenticates. Gets you from install to first result.
/openspec-apply
Implement an approved OpenSpec change and keep tasks in sync.
/openspec-archive
Archive a deployed OpenSpec change and update specs.