gmail-mcp-multi: Instructions file for Claude Code

CLAUDE.md

gmail-mcp-multi CLAUDE.md is an instructions file for Claude Code from dmorrill/gmail-mcp-multi. It costs 248 tokens per session, scanned A, original, MIT.

A CLAUDE.md guide for a TypeScript MCP server that lets AI assistants use several Gmail accounts. Gmail is Google's email service, and MCP is a standard way for an AI assistant to call external tools.

In plain words
What is it for?
Use it when building or testing Gmail search, reading, sending, labelling, and account-authentication features across personal and work mailboxes.
Why use it?
It documents the account model, Google sign-in process, local credential storage, available email operations, and development commands. This makes the multi-account design and current project status clear.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is dmorrill/gmail-mcp-multi's own configuration. It tells Claude Code how to work on gmail-mcp-multi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gmail-mcp-multi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dmorrill/gmail-mcp-multi. 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/dmorrill/gmail-mcp-multi/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dmorrill/gmail-mcp-multi

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 gmail-mcp-multi CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dmorrill/gmail-mcp-multi/claude-md/github.svg)](https://agentmods.dev/instructions/dmorrill/gmail-mcp-multi/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dmorrill/gmail-mcp-multi/claude-md"><img src="https://agentmods.dev/badge/instructions/dmorrill/gmail-mcp-multi/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.

agentmods 80×15 button for gmail-mcp-multi CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dmorrill/gmail-mcp-multi/claude-md"><img src="https://agentmods.dev/badge/instructions/dmorrill/gmail-mcp-multi/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 248 This file is loaded in full into every session.
When invoked 248 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00248 $0.00248
Opus 5.5 $0.00099 $0.00099
Sonnet 5.5 $0.00050 $0.00050
Haiku 4.5 $0.00025 $0.00025

Measured 2mo ago against content hash 9b772df4a4a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gmail-mcp-multi 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 · 34 lines

What it actually says

Gmail MCP Multi — Claude Development Guidelines

What This Is

MCP server that provides Gmail access across multiple accounts. Lets AI assistants search, read, send, and manage email across personal and work accounts with a single tool.

Tech Stack

  • Runtime: Node.js, TypeScript
  • Protocol: MCP (Model Context Protocol) via @modelcontextprotocol/sdk
  • Auth: Google OAuth 2.0 (browser-based flow)
  • Storage: Local JSON file for credentials

Architecture Principles

  • Each account has a friendly alias (e.g., "personal", "work")
  • OAuth tokens stored locally, auto-refreshed
  • Tools are MCP-standard: list_accounts, authenticate, search_emails, read_email, send_email, modify_email, list_labels
  • All tools take an account parameter to specify which mailbox

Current State

  • PR #7 has the full initial implementation ready to merge
  • Closes issues #1-#5
  • Needs testing with real Gmail accounts before merge

Development

npm install
npm run build
npm run dev  # for watch mode

Testing

npm test
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. 2mo ago First seen · 34 lines · 248 tokens per session scan A 9b772df4a4a2

Subscribe to this mod's changes

gmail-mcp-multi CLAUDE.md is an instructions file published in the GitHub repository dmorrill/gmail-mcp-multi (9 stars, last pushed 8mo ago), licensed MIT. It adds 248 tokens to every session, about $0.0010 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.

Related

gmail-mcp-multi CLAUDE.md compared with instructions from other repositories

gmail-mcp-multi CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gmail-mcp-multi CLAUDE.mddmorrill/gmail-mcp-multiInstructions file98mo agoMITA248Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file279ktodayMITA4,325Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot