What is gmail-multi-mcp CLAUDE.md?

Development instructions for a TypeScript Gmail MCP server and its command-line tool. The server connects to Gmail using OAuth 2.0, a permission process that lets an app access an account securely.

Use them when building, running, or modifying the Gmail server or its account-management CLI.

They give contributors one place to check the project structure, dependencies, build commands, development mode, and CLI setup.

How ishaan-skyacres/gmail-multi-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ishaan-skyacres/gmail-multi-mcp. 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/ishaan-skyacres/gmail-multi-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ishaan-skyacres/gmail-multi-mcp

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/ishaan-skyacres/gmail-multi-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ishaan-skyacres/gmail-multi-mcp/claude-md)

Your own site

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

Per session 1,822 This file is loaded in full into every session.

When invoked 1,822 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	$0.01822	$0.01822
Opus 5.5	$0.00729	$0.00729
Sonnet 5.5	$0.00364	$0.00364
Haiku 4.5	$0.00182	$0.00182

Measured 2mo ago against content hash d50e11d25028, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gmail-multi-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 2mo 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 · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 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.

Project Overview

This is a Gmail MCP (Model Context Protocol) Server built in TypeScript. It provides a local MCP server that integrates with Gmail using OAuth 2.0 authentication, allowing Claude to interact with Gmail through secure API calls.

Key Dependencies

@modelcontextprotocol/sdk: Core MCP framework for building servers
googleapis: Google's official Node.js client library for Gmail API
@google-cloud/local-auth: Google's OAuth 2.0 client for desktop applications
commander: CLI framework for the account management tool (argument mode)
@clack/prompts: Interactive terminal prompts with select menus, spinners, and styled output
picocolors: Lightweight terminal color library
zod: Schema validation for tool parameters
nodemailer: RFC 822 email construction with attachment support
mime-types: MIME type detection for attachments

Development Commands

# Build both MCP server and CLI (optional - Bun runs TS natively)
bun run build

# Build CLI only
bun run build:cli

# Development mode with hot reload
bun run dev

# Run CLI in interactive mode (no args = arrow-key menu)
bun src/cli.ts

# Run CLI in argument mode (Commander.js)
bun src/cli.ts list
bun src/cli.ts add [email protected]
bun src/cli.ts default
bun src/cli.ts reauth [email protected]

# Test the MCP server with inspector
bun run inspect

# Type-check without emitting
bun run typecheck

# Run tests
bun test

Architecture

The project follows a modular architecture:

Entry Point: src/index.ts - Main MCP server setup and tool definitions
CLI: src/cli.ts - Dual-mode CLI: interactive (no args) or Commander.js (with args)
Interactive CLI: src/interactive.ts - Arrow-key navigable menu using @clack/prompts
Gmail Client: src/gmail-client.ts - Gmail API wrapper (send, search, read, modify, delete, batch ops, attachments)
Account Manager: src/account-manager.ts - Multi-account credential storage and switching
Email Utils: src/email-utils.ts - MIME encoding, email validation, path security, Nodemailer integration
Label Manager: src/label-manager.ts - CRUD operations for Gmail labels
Filter Manager: src/filter-manager.ts - Gmail filter CRUD and pre-built templates
Authentication: src/auth.ts - OAuth 2.0 credential management
Types: src/types.ts - TypeScript interfaces and type definitions

Read the full file on GitHub · 188 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.

2mo ago First seen · 188 lines · 1,822 tokens per session scan A d50e11d25028

Subscribe to this mod's changes

gmail-multi-mcp CLAUDE.md is an instructions file published in the GitHub repository ishaan-skyacres/gmail-multi-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,822 tokens to every session, about $0.0073 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.

claude email gmail mcp model-context-protocol multi-account

gmail-multi-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gmail-multi-mcp CLAUDE.mdishaan-skyacres/gmail-multi-mcp	Instructions file	0	3mo ago	MIT	A	1,822	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gmail-multi-mcp: Instructions file for Claude Code