google_workspace_fastmcp2: Skill for Claude Code

.claude/skills/google-workspace-mcp/SKILL.md

google-workspace-mcp is a skill for Claude Code from dipseth/google_workspace_fastmcp2. It costs 31 tokens per session (6,115 once invoked), scanned A, original, Apache-2.0.

A usage guide for the Google Workspace MCP server, which connects an agent to Google services and provides tools for emails, Chat cards, code execution, and search.

In plain words
What is it for?
Use it to compose or send emails, create Chat cards, run sandboxed code, manage available tools, and search stored responses.
Why use it?
It explains the server's notation, macros, parameters, and tool-management rules so requests are formed correctly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is dipseth/google_workspace_fastmcp2's own configuration. It tells Claude Code how to work on google_workspace_fastmcp2 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_fastmcp2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dipseth/google_workspace_fastmcp2. 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/dipseth/google_workspace_fastmcp2/main/.claude/skills/google-workspace-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dipseth/google_workspace_fastmcp2

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/dipseth/google_workspace_fastmcp2/google-workspace-mcp.svg)](https://agentmods.dev/skills/dipseth/google_workspace_fastmcp2/google-workspace-mcp)
Your own site
<a href="https://agentmods.dev/skills/dipseth/google_workspace_fastmcp2/google-workspace-mcp"><img src="https://agentmods.dev/badge/skills/dipseth/google_workspace_fastmcp2/google-workspace-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,115 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00031 $0.06115
Opus 5 $0.00015 $0.03057
Sonnet 5 $0.00006 $0.01223
Haiku 4.5 $0.00003 $0.00611

Measured 7d ago against content hash 8a9249f7641d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

google-workspace-mcp 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 7d 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.

.claude/skills/google-workspace-mcp/SKILL.md · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Workspace MCP Server

FastMCP-based Google Workspace server with DSL-driven composition for emails and chat cards, sandboxed code execution, Jinja2 macros, privacy middleware, and Qdrant-backed response history. Not all tools are active at any given time — use manage_tools(action="list") to see what's currently enabled.

Core Wrapped Tools

compose_dynamic_email — MJML Email Composer

Composes responsive HTML emails via DSL notation, then sends or saves as draft.

Parameters:

Parameter Type Default Description
email_description str required DSL structure ONLY + optional subject. Text after the DSL becomes the email subject (e.g., ε[ħ, τ] Welcome aboard)
email_params dict/str None REQUIRED for content — block text/titles/URLs go here, keyed by symbol. email_description is structure ONLY. Also accepts subject and preheader keys. Supports _shared/_items merging
to str/list "myself" Recipients: "myself", comma-separated string, or list of emails
user_google_email str None Auto-injected from OAuth session. Pass only to override (e.g., for secondary accounts)
action "send"/"draft" "draft" Draft is safe default; "send" delivers immediately
cc / bcc str None Optional CC/BCC recipients
reply_to_message_id str None Thread the composed email as a reply to this Gmail message. Recipients derive from the original; the reply subject overrides the DSL subject
draft_id str None Update an existing draft in place with the freshly rendered email instead of creating a new one (action='draft' only)

Email DSL Symbols:

Symbol Block
ε EmailSpec
ħ HeroBlock
τ TextBlock
Ƀ ButtonBlock
ɨ ImageBlock
¢ ColumnsBlock
© Column
Ħ HeaderBlock
ƒ FooterBlock
đ DividerBlock
ş SpacerBlock
ą AccordionBlock
ȼ CarouselBlock
ʂ SocialBlock
ƭ TableBlock

Read the full file on GitHub · 514 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. 7d ago First seen · 514 lines · 31 tokens per session scan A 8a9249f7641d

Subscribe to this mod's changes

google-workspace-mcp is a skill published in the GitHub repository dipseth/google_workspace_fastmcp2 (25 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 6,115 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 2026-08-30.