What is MultiGmailMCP CLAUDE.md?

Project instructions for MultiGmailMCP, a local MCP server that connects coding agents to Gmail and Google Calendar accounts.

Use them when changing account handling, Gmail or Calendar tools, OAuth setup, the local setup page, or the server. They also define the required layout and verification steps.

They explain where account credentials, API wrappers, server tools, and setup code belong, while documenting safeguards for sending messages and calendar invitations.

How leandro-santos-abreu/MultiGmailMCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to leandro-santos-abreu/MultiGmailMCP. 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/leandro-santos-abreu/MultiGmailMCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/leandro-santos-abreu/MultiGmailMCP

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/leandro-santos-abreu/multigmailmcp/claude-md/github.svg)](https://agentmods.dev/instructions/leandro-santos-abreu/multigmailmcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/leandro-santos-abreu/multigmailmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/leandro-santos-abreu/multigmailmcp/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/leandro-santos-abreu/multigmailmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/leandro-santos-abreu/multigmailmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,834 This file is loaded in full into every session.

When invoked 1,834 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	$0.01834	$0.01834
Opus 5	$0.00917	$0.00917
Sonnet 5	$0.00367	$0.00367
Haiku 4.5	$0.00183	$0.00183

Measured 9d ago against content hash cf6f191dcd2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

MultiGmailMCP 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 9d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

See @README.md for what this project is and the full end-user setup walkthrough. This file is for whoever — human or Claude — edits the code; it's deliberately not a duplicate of the README.

Layout

accounts.py — token storage/loading/refresh, defines SCOPES
gmail_client.py — thin Gmail API wrapper; every function takes account_name first and resolves credentials itself via accounts.load_credentials
calendar_client.py — thin Google Calendar v3 wrapper, same pattern as gmail_client; backs the calendar_* tools (specs/014). Notifying attendees (send_updates="all") is the Gmail-"send" analog: gated by GMAIL_MCP_SEND_PHRASE and audited.
server.py — MCP tool definitions (stdio transport); thin wrappers around gmail_client
add_account.py — one-time interactive OAuth CLI, not imported by the server
setup_app.py — optional local web UI (stdlib http.server) for setup/account management; standalone tooling, not imported by the server; reuses accounts/gmail_client; localhost-only + one-time-token gated; never renders token/credentials contents (specs/012)
main.py — packaging entry point with serve (stdio server) / setup (UI) subcommands; what the built executable runs (specs/013). build.py packages it with PyInstaller. serve hides the console window on Windows so it runs headless when Claude Desktop launches it; a no-argument launch (double-click) opens setup.
version.py — single source of truth for __version__; bump it in lockstep with the release tag (specs/015)
updates.py — best-effort GitHub-release update check (notify-only, stdlib, cached in DATA_DIR). Feeds the setup-UI banner, the check_for_updates tool, and the session-start "update available" note in the server instructions. GMAIL_MCP_NO_UPDATE_CHECK=1 disables it. Never on serve's stdout (specs/015)
tests/ — pytest suite (132 tests) that mocks gmail_client._service, so it runs offline with no real credentials or token files. Covers the pure helpers, the AccountError convention, every tool group (read/draft/organize/settings/forwarding/attachments), the send audit + confirm gate, the setup UI's request handling, and the packaging data-dir/dispatch logic. The live-account manual loop below still covers what a fake can't (real OAuth/refresh, an actual send, a real PyInstaller build).

Read the full file on GitHub · 55 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.

9d ago First seen · 55 lines · 1,834 tokens per session scan A cf6f191dcd2a

Subscribe to this mod's changes

MultiGmailMCP CLAUDE.md is an instructions file published in the GitHub repository leandro-santos-abreu/MultiGmailMCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,834 tokens to every session, about $0.0092 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

MultiGmailMCP: Instructions file for Claude Code