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.
curl -O https://raw.githubusercontent.com/dipseth/google_workspace_fastmcp2/main/.claude/skills/google-workspace-mcp/SKILL.mdgit clone --depth 1 https://github.com/dipseth/google_workspace_fastmcp2Wrote 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/skills/dipseth/google_workspace_fastmcp2/google-workspace-mcp)<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>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 5.1 | $0.00031 | $0.06115 |
| Opus 5 | $0.00015 | $0.03057 |
| Sonnet 5 | $0.00006 | $0.01223 |
| Haiku 4.5 | $0.00003 | $0.00611 |
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.
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 |
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.
- 7d ago First seen · 514 lines · 31 tokens per session scan A 8a9249f7641d
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.