mcp-google-gmail CLAUDE.md

mcp-google-gmail CLAUDE.md is an instructions file for Claude Code from A1-x-Tech/mcp-google-gmail. It costs 2,486 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for developing an MCP server that connects to one Gmail mailbox through Google's Gmail API. It documents commands, architecture, conventions, authentication, and how to add tools.

In plain words
What is it for?
Developing, testing, type-checking, building, and extending Gmail features such as searching mail, reading messages, sending mail, managing drafts and labels, and moving messages to trash.
Why use it?
It gives contributors the project rules needed to change the Gmail integration without breaking its safety and testing expectations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

Install

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.

agentmods
npx agentmods add instructions/a1-x-tech/mcp-google-gmail/claude-md
Clone the repo
git clone --depth 1 https://github.com/A1-x-Tech/mcp-google-gmail

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.

agentmods badge for mcp-google-gmail CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/a1-x-tech/mcp-google-gmail/claude-md.svg)](https://agentmods.dev/instructions/a1-x-tech/mcp-google-gmail/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/a1-x-tech/mcp-google-gmail/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-google-gmail/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,486 This file is loaded in full into every session.
When invoked 2,486 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02486 $0.02486
Opus 5 $0.01243 $0.01243
Sonnet 5 $0.00497 $0.00497
Haiku 4.5 $0.00249 $0.00249

Measured 5d ago against content hash ff1c75a02558, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-google-gmail 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 5d 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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-google-gmail

MCP server for the Gmail API v1 (TypeScript, stdio). Mixed read/write: tools cover message/thread search and decoded reading, sending (direct and via drafts), the full draft lifecycle, labels and the reversible trash; raw_request is the escape hatch. The server talks to https://gmail.googleapis.com (always users/me — one mailbox) with a Bearer token; the token is minted from an OAuth2 refresh token via https://oauth2.googleapis.com/token (or a static GOOGLE_GMAIL_ACCESS_TOKEN, mostly for testing). There is deliberately no permanent message delete — the trash is the safety net.

Commands

npm run dev        # run from source (tsx watch)
npm test           # unit tests + dist smoke, no network
npm run typecheck  # types for src + tests
npm run build      # emit dist/
npm run smoke      # live check: read-only profile fetch; GOOGLE_GMAIL_SMOKE_WRITE=1 adds a disposable-draft roundtrip with cleanup in finally

Architecture

  • src/config.ts — env → config. Credentials: either the refresh triple GOOGLE_GMAIL_CLIENT_ID + GOOGLE_GMAIL_CLIENT_SECRET + GOOGLE_GMAIL_REFRESH_TOKEN (all three or ConfigError incomplete_oauth_config) or GOOGLE_GMAIL_ACCESS_TOKEN; optional GOOGLE_GMAIL_API_BASE, GOOGLE_GMAIL_TIMEOUT_MS, GOOGLE_GMAIL_MAX_RETRIES. No credentials at all is NOT an error: the fields stay undefined and the server starts degraded. Also home to CredentialsError / MISSING_CREDENTIALS_MESSAGE (opens with the historical startup error verbatim, then names the variables and the restart) and hasCredentials().
  • src/client.ts — all HTTP and all wire mapping. Token lifecycle (cache until ~60s before expiry, dedupe concurrent refreshes, one forced re-mint + replay on 401); request() resolves the path against the base and rejects foreign origins (SSRF guard), enforces an AbortController timeout that also covers reading the body, retries 429 always but 5xx/network errors only for GET — replaying a send after an ambiguous failure would double-send — and throws GoogleGmailError(status, body). The MIME layer lives here too: buildMimeMessage() (RFC 2822 with base64 bodies, multipart/alternative, RFC 2047 subject, header-injection guard, reply headers) and decodeMessage() (base64url + charset decode, RFC 2047 header decode, attachment metadata, maxBodyChars truncation with flags). buildLabelChanges() maps the normalized read/starred/archived flags to UNREAD/STARRED/INBOX label operations.
  • src/tools/messages.tslist_messages (search + metadata hydration), get_message, send_message, modify_message, manage_trash (trash/untrash × message/thread). src/tools/threads.tslist_threads, get_thread, modify_thread. src/tools/drafts.tscreate_draft, list_drafts, get_draft, update_draft (full replacement — the API has no partial draft edit), send_draft, delete_draft (permanent — drafts skip the trash). src/tools/labels.tslist_labels (list, or one label with counts), manage_labels (create/update/delete). src/tools/profile.tsget_profile. src/tools/raw.tsraw_request (GET/POST/PUT/PATCH/DELETE). src/tools/util.tsok/fail, the four annotation presets (READ_ONLY/WRITE/UPDATE/DESTRUCTIVE) and shared zod schema factories (messageIdSchema, recipientSchema, gmailQuerySchema, ...).
  • src/index.ts — wires every register* into the McpServer. loadConfigOrDegraded() catches ConfigError, pings startup_failed (fire-and-forget) and degrades the config to "no credentials"; an unconfigured start prepends UNCONFIGURED_PREFIX — plus Configuration problem: <message> when a ConfigError was caught — to the initialize instructions, and oninitialized sends server_start for a configured install or unconfigured_start (with the reason) otherwise.
  • src/telemetry.ts — anonymous usage pings (ids/names/versions only, never mail or arguments; fire-and-forget, must never block or throw; opt-out ASKADS_TELEMETRY=0). server_start means "a usable install started"; unconfigured_start is a degraded start and startup_failed a malformed config caught at load — both carry a reason from a closed vocabulary (missing_credentials, incomplete_oauth_config) — never a variable's name or value.

Read the full file on GitHub · 142 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.

  1. 5d ago First seen · 142 lines · 2,486 tokens per session scan A ff1c75a02558

Subscribe to this mod's changes

mcp-google-gmail CLAUDE.md is an instructions file published in the GitHub repository A1-x-Tech/mcp-google-gmail (0 stars, last pushed 6d ago), licensed MIT. It adds 2,486 tokens to every session, about $0.0124 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens