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 agentmods add instructions/synclyai/gmail-mcp/claude-mdgit clone --depth 1 https://github.com/SynclyAI/gmail-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/instructions/synclyai/gmail-mcp/claude-md)<a href="https://agentmods.dev/instructions/synclyai/gmail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/synclyai/gmail-mcp/claude-md.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 | $0.00628 | $0.00628 |
| Opus 5 | $0.00314 | $0.00314 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
gmail-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 3d 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 — 58 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.
Build and Test Commands
npm run build # TypeScript compilation
npm test # Run all tests
npm run test:watch # Run tests in watch mode
npx vitest run src/auth/session.test.ts # Run single test file
npm run dev # Development mode with tsx watch
npm start # Run compiled server
Architecture
Gmail MCP Server with read-only access and label-based filtering. Implements MCP SDK's OAuth 2.1 with PKCE for authentication.
Two-Tier OAuth Flow
The server bridges Google OAuth with MCP OAuth:
- MCP Client → Server: Client initiates OAuth via
mcpAuthRouter(standard MCP SDK flow) - Server → Google:
GmailOAuthServerProvider.authorize()creates pending request, redirects to Google - Google → Server:
/callbackreceives Google auth code,oauth-bridge.getRedirectUrl()exchanges it for tokens - Server → MCP Client: Returns MCP auth code, client exchanges for session token (used as bearer token)
Session token (not Google access token) is the MCP bearer token. Google tokens are stored server-side in SessionStore.
Key Components
src/index.ts- Express HTTPS server setup, registers routessrc/auth/gmail/oauth-provider.ts-GmailOAuthServerProviderimplements MCP SDK'sOAuthServerProvider, manages pending auth requests and auth codessrc/auth/gmail/oauth-handler.ts- Google OAuth operations (auth URL, token exchange, refresh)src/auth/session.ts-SessionStoremanages session lifecycle (temp → active), stores Google tokenssrc/auth/routes.ts- OAuth endpoints viamcpAuthRouter,/callbackfor Google redirectsrc/mcp/routes.ts-/mcpendpoint with bearer auth and labels middlewaresrc/mcp/server.ts-GmailMCPServerhandles MCP tool requestssrc/gmail/client.ts-GmailClientwraps Gmail API with label filtering
Label-Based Access Control
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.
- 3d ago First seen · 58 lines · 628 tokens per session scan A cf9b2c8ad496
gmail-mcp CLAUDE.md is an instructions file published in the GitHub repository SynclyAI/gmail-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 628 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.