What is gmail-mcp-server CLAUDE.md?

A set of project instructions for Claude Code working on a Gmail MCP server. The server connects Claude to Gmail and provides tools for email, drafts, labels, searches, attachments, and settings.

For guiding code changes to the Gmail server, including its OAuth setup, email operations, and configuration.

It gives the coding agent the project structure, architecture decisions, and authentication details it needs to work in the repository.

How kovvurisupraj/gmail-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kovvurisupraj/gmail-mcp-server. 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/kovvurisupraj/gmail-mcp-server/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kovvurisupraj/gmail-mcp-server

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/kovvurisupraj/gmail-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/kovvurisupraj/gmail-mcp-server/claude-md)

Your own site

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

Per session 1,282 This file is loaded in full into every session.

When invoked 1,282 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	$0.01282	$0.01282
Opus 5	$0.00641	$0.00641
Sonnet 5	$0.00256	$0.00256
Haiku 4.5	$0.00128	$0.00128

Measured 8d ago against content hash 0a3c185d14b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gmail-mcp-server 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.

CLAUDE.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — gmail-mcp-server

Project context for Claude Code sessions.

What This Project Is

A production-ready npm-publishable MCP (Model Context Protocol) server that connects Claude AI to Gmail. Users add it to Claude Desktop and get 30 Gmail tools available via natural language.

Project Structure

src/
  index.ts              Entry point — CLI routing + MCP server start
  auth.ts               getGmailClient() — loads config + token, returns Gmail client
  config.ts             Load/save ~/.gmail-mcp/config.json (OAuth credentials)
  setup/
    server.ts           Express server — browser-based first-time setup UI
    ui.ts               Self-contained HTML for the setup page (returned as string)
  tools/
    index.ts            dispatchTool() — pre-flight auth check + routes to handlers
    messages.ts         12 email tools (list, get, send, reply, forward, trash, etc.)
    drafts.ts           6 draft tools
    labels.ts           6 label tools
    search.ts           3 search/thread tools
    attachments.ts      2 attachment tools
    settings.ts         6 settings tools (vacation responder, filters)
  utils/
    email.ts            RFC 2822 encoding, MIME body extraction helpers
    token.ts            Multi-account token storage (per-email JSON files)
    port.ts             findAvailablePort(start) — tries 3000–3010
scripts/
  auth-setup.ts         Thin shim — now forwards to startSetupServer()

Key Architecture Decisions

Auth flow

Credentials (CLIENT_ID, CLIENT_SECRET) live in ~/.gmail-mcp/config.json
Per-account tokens live in ~/.gmail-mcp/tokens/{email}.json
accounts.json is the registry of connected accounts
getGmailClient() throws 'SETUP_REQUIRED' (no config) or 'AUTH_REQUIRED' (no token)
Those errors are caught in dispatchTool() in tools/index.ts — auto-opens the setup browser UI

Setup server

Express server on port 3000 (tries 3001–3010 if busy)
GET / → shows setup form (or redirects to /auth/start if config already exists)
POST /setup → saves CLIENT_ID + CLIENT_SECRET to config.json
GET /auth/start → generates Google OAuth URL, redirects browser to Google
GET /callback → exchanges code for token, saves to disk, shuts server down
serverRunning guard prevents multiple instances
When called fire-and-forget from a tool handler, the MCP server keeps running in parallel

Read the full file on GitHub · 127 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.

8d ago First seen · 127 lines · 1,282 tokens per session scan A 0a3c185d14b2

Subscribe to this mod's changes

gmail-mcp-server CLAUDE.md is an instructions file published in the GitHub repository kovvurisupraj/gmail-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,282 tokens to every session, about $0.0064 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.

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 · 5,153 tokens

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

gmail-mcp-server: Instructions file for Claude Code