Borrowing it
Nothing to install: this file belongs to toantran201/mcp-google-sheets. 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/toantran201/mcp-google-sheets/master/CLAUDE.mdgit clone --depth 1 https://github.com/toantran201/mcp-google-sheetsWrote 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/instructions/toantran201/mcp-google-sheets/claude-md)<a href="https://agentmods.dev/instructions/toantran201/mcp-google-sheets/claude-md"><img src="https://agentmods.dev/badge/instructions/toantran201/mcp-google-sheets/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.
<a href="https://agentmods.dev/instructions/toantran201/mcp-google-sheets/claude-md"><img src="https://agentmods.dev/badge/instructions/toantran201/mcp-google-sheets/claude-md.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 | $0.02813 | $0.02813 |
| Opus 5.5 | $0.01125 | $0.01125 |
| Sonnet 5.5 | $0.00563 | $0.00563 |
| Haiku 4.5 | $0.00281 | $0.00281 |
Grade A, and why
mcp-google-sheets 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 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.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
An MCP (Model Context Protocol) stdio server that gives AI agents read/write access to Google Spreadsheets. Two auth modes, auto-detected from env: per-user OAuth (browser sign-in, edits attributed to the real user) or Service Account (headless JWT, legacy). There is no fixed target spreadsheet — every tool takes a required spreadsheet parameter (URL or ID). Written in TypeScript, ESM-only, bundled with tsup.
Commands
npm run dev # Run directly from TypeScript via tsx (no build) — primary dev loop
npm run build # Bundle src/index.ts → dist/index.js with tsup
npm start # Run the built server (node dist/index.js)
npm run typecheck # tsc --noEmit (type validation)
npm run lint # eslint .
npm run format # prettier --write . (format:check to verify without writing)
npx tsx src/test-tools.ts <spreadsheet-url-or-id> # Manual end-to-end test: hits a REAL Google Sheet
There is no unit test framework. Linting (ESLint flat config, eslint.config.js), formatting (Prettier, .prettierrc.json — single quotes, markdown ignored) and typechecking scripts exist; run them before committing. test-tools.ts is a manual integration harness that runs every tool handler against the live spreadsheet passed as argv[2] (or TEST_SPREADSHEET env). It creates a TestTab_<timestamp> sheet and writes rows — expect side effects on the real sheet. Run it to verify changes end-to-end.
Requires a .env (copy .env.example) with ONE auth mode:
- OAuth:
GOOGLE_OAUTH_CLIENT_ID+GOOGLE_OAUTH_CLIENT_SECRET(wins if both modes are set) - Service Account:
GOOGLE_SERVICE_ACCOUNT_EMAIL+GOOGLE_PRIVATE_KEY
Optional: TOOLS (comma-separated allowlist), USER_NAME (stamped onto add_rows writes). SPREADSHEET_ID no longer exists.
Architecture
Startup flow (src/index.ts): loadConfig() → new AuthManager(config) → new SheetsClient(authManager) → registerAllTools(server, client, config) → connect stdio transport. Diagnostics go to console.error (stdout is reserved for the MCP protocol — never write to it, and never prompt on it).
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 Changed · +2 lines · +220 tokens per session becafab15a17
- 2mo ago First seen · 95 lines · 2,593 tokens per session scan A dea63c269193
mcp-google-sheets CLAUDE.md is an instructions file published in the GitHub repository toantran201/mcp-google-sheets (0 stars, last pushed 8d ago), licensed MIT. It adds 2,813 tokens to every session, about $0.0113 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.
mcp-google-sheets CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-google-sheets CLAUDE.mdtoantran201/mcp-google-sheets | Instructions file | 0 | 8d ago | MIT | A | 2,813 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |