What is gws-mcp CLAUDE.md?

Project-specific instructions for developing a Google Workspace connection for Claude, covering its architecture, commands, conventions, and tests. Google Workspace includes services such as Gmail, Calendar, Drive, Sheets, and Docs.

Use it when changing the TypeScript code, running development or test commands, building the extension, handling its command-line connection, or following its import and output-folder rules.

It gives contributors one place to check how the project is structured and how changes should be built, tested, and packaged.

How datatorag/gws-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to datatorag/gws-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/datatorag/gws-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/datatorag/gws-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/datatorag/gws-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/datatorag/gws-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/datatorag/gws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/datatorag/gws-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/datatorag/gws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/datatorag/gws-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,115 This file is loaded in full into every session.

When invoked 1,115 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01115	$0.01115
Opus 5.5	$0.00446	$0.00446
Sonnet 5.5	$0.00223	$0.00223
Haiku 4.5	$0.00112	$0.00112

Measured 1mo ago against content hash c437477f9ad3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gws-mcp CLAUDE.md 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 1mo 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.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project

Google Workspace MCP extension for Claude. Calls the Google REST APIs directly (the gws CLI remains only as a no-token self-host fallback and for login) to expose 68 tools (Gmail, Calendar, Drive, Contacts, Sheets, Docs, Slides, Tasks, generic API access) via MCP.

Commands

pnpm run build — compile TypeScript (src/ → server/)
pnpm run dev — watch mode
pnpm run build:extension — compile + pack into google-workspace-mcp.mcpb
pnpm run download-binaries — fetch gws binaries into bin/ (opt-in: needed for self-hosted login, the no-token fallback, and the oracle test; build no longer runs it)
node scripts/generate-method-table.mjs — regenerate src/google-api/method-table.ts from Google's Discovery documents

Architecture

Two entry points sharing createMcpServer() from create-server.ts:

extension.ts — stdio transport for .mcpb (Claude Desktop). Auto-triggers browser OAuth login on first run.
index.ts — HTTP transport on port 39147 for Claude Code / standalone use.

gws-client.ts is the client every tool calls. With a bearer token (every hosted call) api() is a fetch built from the generated method table in src/google-api/; it never spawns a process and never loads the CLI. With no token it falls back to cli-transport.ts, which wraps the gws binary (Rust, in bin/) and also owns the login flow. src/google-api/oracle.test.ts holds the request builder equal to the pinned CLI's --dry-run for every method; it fails, not skips, when the binary is missing. The token goes in the Authorization header only. OAuth client ID and secret are read from GWS_OAUTH_CLIENT_ID / GWS_OAUTH_CLIENT_SECRET env vars and passed to the binary on the fallback path.

Key conventions

ESM ("type": "module"), all imports use .js extensions
TypeScript strict mode, target ES2024, NodeNext module resolution
Output dir is server/ (not dist/)
Use pnpm, not npm
Tests: pnpm test (vitest — typechecks the test files, then runs them). Unit tests live beside the module and drive handlers through a fake { api } client, so they need no network. They cannot catch a changed upstream response shape: a live smoke test against the real API is still the verification for anything touching a Google endpoint.

Read the full file on GitHub · 77 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.

1mo ago Changed · +1 lines · +197 tokens per session c437477f9ad3
1mo ago Changed 25d5751f95cf
2mo ago First seen · 76 lines · 918 tokens per session scan A 604854cea8bc

Subscribe to this mod's changes

gws-mcp CLAUDE.md is an instructions file published in the GitHub repository datatorag/gws-mcp (2 stars, last pushed 27d ago), licensed MIT. It adds 1,115 tokens to every session, about $0.0045 per session on Opus 5.5. 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.

gws-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gws-mcp CLAUDE.mddatatorag/gws-mcp	Instructions file	2	27d ago	MIT	A	1,115	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gws-mcp: Instructions file for Claude Code