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 skills add WorldCentralKitchen/google_workspace_mcp --skill managing-google-workspacegit clone --depth 1 https://github.com/WorldCentralKitchen/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/skills/worldcentralkitchen/google_workspace_mcp/managing-google-workspace)<a href="https://agentmods.dev/skills/worldcentralkitchen/google_workspace_mcp/managing-google-workspace"><img src="https://agentmods.dev/badge/skills/worldcentralkitchen/google_workspace_mcp/managing-google-workspace/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.
<a href="https://agentmods.dev/skills/worldcentralkitchen/google_workspace_mcp/managing-google-workspace"><img src="https://agentmods.dev/badge/skills/worldcentralkitchen/google_workspace_mcp/managing-google-workspace.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00123 | $0.02724 |
| Opus 5 | $0.00062 | $0.01362 |
| Sonnet 5 | $0.00025 | $0.00545 |
| Haiku 4.5 | $0.00012 | $0.00272 |
Grade B, and why
managing-google-workspace scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Direct the user to edit `~/.claude/settings.local.json` themselves (this file is gitignored and never shared). Do not ask the user to paste secrets into the conversation. Tell them to add the following to the `env` block This is a copy
94% identical to managing-google-workspace — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace -- Tool Router
Execution Mode
Detect which mode is available and use it.
MCP (preferred)
If MCP tools from the google-workspace server are available, call them directly. The tool names in the tables below are the base names -- prefix with the server name as needed (e.g. google-workspace:search_gmail_messages).
CLI (no MCP)
If no MCP tools are available, execute via bash:
uvx workspace-mcp --cli <tool_name> --args '{"user_google_email": "USER_EMAIL", ...}'
Before calling a tool, read the relevant reference file for exact parameter names and types. Only use parameters documented there -- do not invent parameters.
First-Time Setup
If a tool call fails with a credential error, walk the user through this setup.
1. Create OAuth credentials
Direct the user to Google Cloud Console:
- Create OAuth 2.0 Client ID (Desktop application type)
- Enable the Google APIs they need (Gmail, Drive, Calendar, etc.)
- Copy the Client ID and Client Secret
2. Store credentials
Direct the user to edit ~/.claude/settings.local.json themselves (this file is gitignored and never shared). Do not ask the user to paste secrets into the conversation. Tell them to add the following to the env block:
{
"env": {
"GOOGLE_OAUTH_CLIENT_ID": "their-client-id",
"GOOGLE_OAUTH_CLIENT_SECRET": "their-secret"
}
}
If settings.local.json already exists, they should merge into the existing env object, not replace it. These env vars are inherited by all MCP servers and CLI processes that Claude Code spawns.
3. Authenticate
- MCP mode: call
start_google_authto open the browser OAuth flow - CLI mode: run any tool -- the first invocation opens the OAuth flow
- Credentials are cached in
~/.google_workspace_mcp/credentials(or as configured byWORKSPACE_MCP_CREDENTIALS_DIR) for future sessions
For server options, transport, auth modes, tool filtering, and deployment: references/server-options.md
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evaluations/edit_doc.json 431 B
- evaluations/search_email.json 359 B
- evaluations/share_file.json 475 B
- references/apps-script.md 6.5 KB
- references/calendar.md 4.2 KB
- references/chat.md 2.9 KB
- references/contacts.md 4.7 KB
- references/docs-layout-workflow.md 7.7 KB
- references/docs.md 16 KB
- references/drive.md 14 KB
- references/forms.md 3.1 KB
- references/gmail.md 9.7 KB
- references/search.md 1.9 KB
- references/server-options.md 5.0 KB
- references/sheets.md 7.5 KB
- references/slides.md 7.3 KB
- references/tasks.md 4.0 KB
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.
- 8d ago First seen · 305 lines · 123 tokens per session scan B 1820888d269c
managing-google-workspace is a skill published in the GitHub repository WorldCentralKitchen/google_workspace_mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 123 tokens to every session and 2,724 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 94% identical to managing-google-workspace, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
wecomcli-sheet
A tool for managing WeCom online spreadsheets, including spreadsheet files, data, and subtables. WeCom is an enterprise collaboration platform.
google-workspace
Access Google Workspace APIs (Drive, Docs, Calendar, Gmail, Sheets, Slides, Chat, People) via local helper scripts without MCP. Handles OAuth login and direct API calls.
gog-workspace
Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.
googleworkspace
Manage Google Drive, Gmail, Calendar, Sheets, Docs, and Chat via the gws CLI.