What is multi-gmail-mcp-server CLAUDE.md?

A set of instructions for Claude Code when working on a TypeScript server that connects multiple Gmail accounts to Claude through the Model Context Protocol (MCP), a standard way for AI tools to use external services.

Use it when developing, starting, or configuring the multi-account Gmail server and its setup commands.

It explains how to build, run, configure, and organize the server, reducing mistakes with Gmail credentials, TypeScript modules, and account management.

multi-gmail-mcp-server CLAUDE.md — Instructions file for coding agents by umesh9883: A set of instructions for Claude Code when working…

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/umesh9883/multi-gmail-mcp-server/claude-md

Clone the repo

git clone --depth 1 https://github.com/umesh9883/multi-gmail-mcp-server

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/umesh9883/multi-gmail-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/umesh9883/multi-gmail-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/umesh9883/multi-gmail-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/umesh9883/multi-gmail-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 648 This file is loaded in full into every session.

When invoked 648 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.

Model	Per session	Once invoked
Fable 5.1	$0.00648	$0.00648
Opus 5	$0.00324	$0.00324
Sonnet 5	$0.00130	$0.00130
Haiku 4.5	$0.00065	$0.00065

Measured 5d ago against content hash 414e387ba485, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

multi-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 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 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.

Commands

npm run build    # Compile TypeScript → dist/
npm run start    # Run the compiled MCP server (requires dist/)
npm run dev      # Run via ts-node without building
npm run setup    # Account management CLI (list/add/remove Gmail accounts)

Setup CLI usage:

npm run setup list
npm run setup add <label>          # e.g. add personal, add work
npm run setup remove <email>

Required env vars before running setup or starting the server:

export GMAIL_CLIENT_ID=...
export GMAIL_CLIENT_SECRET=...

Architecture

This is a Model Context Protocol (MCP) server that aggregates multiple Gmail accounts and exposes them as tools to Claude.

Module system

TypeScript compiles to CommonJS (no "type": "module" in package.json)
tsconfig.json uses "module": "NodeNext" + "moduleResolution": "NodeNext" — required to resolve the @modelcontextprotocol/sdk package's exports field (the SDK has "type": "module" with both ESM and CJS builds)
All relative imports in source files use .js extensions (NodeNext requirement)

Source structure

src/
  index.ts          — Entry point: creates McpServer, registers tools, connects via stdio
  setup.ts          — CLI for account management (add/list/remove)
  types.ts          — All shared TypeScript interfaces
  constants.ts      — Scopes, redirect URI, limits
  services/
    auth.ts         — OAuth2 flow: browser-based login, token exchange, auto-refresh
    token-store.ts  — AES-256-GCM encrypted file store at ~/.multi-gmail-mcp/tokens.enc
    gmail-client.ts — Gmail API wrappers: searchMessages, readMessage, readThread, getProfile
  tools/
    account-tools.ts — MCP tools: gmail_list_accounts, gmail_remove_account
    search-tools.ts  — MCP tools: gmail_search_all, gmail_search, gmail_read_message, gmail_read_thread

Key design decisions

Token storage: Tokens are encrypted with AES-256-GCM using a key derived from hostname + username via SHA-256. Stored at ~/.multi-gmail-mcp/tokens.enc (mode 600). This is NOT the OS keychain — it's a file-based encrypted store.

Read the full file on GitHub · 62 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.

5d ago First seen · 62 lines · 648 tokens per session scan A 414e387ba485

Subscribe to this mod's changes

multi-gmail-mcp-server CLAUDE.md is an instructions file published in the GitHub repository umesh9883/multi-gmail-mcp-server (1 stars, last pushed 5mo ago), licensed MIT. It adds 648 tokens to every session, about $0.0032 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.

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 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

multi-gmail-mcp-server CLAUDE.md