gmail-mcp-server: Instructions file for Gemini CLI

GEMINI.md

gmail-mcp-server GEMINI.md is an instructions file for Gemini CLI from jnpacker/gmail-mcp-server. It costs 1,299 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a Gmail MCP server and its web dashboard. Gmail is Google's email service; an MCP server lets AI assistants use tools, while the dashboard is a browser interface for email triage.

In plain words
What is it for?
Setting up Google Cloud credentials, running Python tests, starting the Flask dashboard, and manually running or scheduling Gmail triage with supported models.
Why use it?
They explain how the repository is organised, how to authenticate with Gmail, how to run tests, and how to start or use its tools.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is jnpacker/gmail-mcp-server's own configuration. It tells Gemini CLI how to work on gmail-mcp-server 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-server configures →

Reuse

Borrowing it

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

Made for: Gemini CLI.

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-server GEMINI.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jnpacker/gmail-mcp-server/gemini-md"><img src="https://agentmods.dev/badge/instructions/jnpacker/gmail-mcp-server/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,299 This file is loaded in full into every session.
When invoked 1,299 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 $0.01299 $0.01299
Opus 5.5 $0.00520 $0.00520
Sonnet 5.5 $0.00260 $0.00260
Haiku 4.5 $0.00130 $0.00130

Measured 2mo ago against content hash 9cfb08231ad5, 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-server GEMINI.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.

GEMINI.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 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.

What This Repo Is

Two loosely coupled systems that share the Gmail API client:

  1. MCP Server (gmail_mcp_server/) — a stdio MCP server exposing Gmail tools to AI assistants (Claude, Gemini). Runs headlessly via .mcp.json.
  2. Web Dashboard (app.py) — a Flask app that invokes triage by spawning gemini -p /triage as a subprocess, parses the structured output, and caches results for the browser UI.

The triage command itself lives in commands/triage.md (symlinked into .claude/commands/ and converted to .gemini/commands/ TOML). The command instructs the AI to call Gmail MCP tools directly.

Commands

# Auth setup (requires credentials.json from Google Cloud Console)
make auth

# Run tests
python -m pytest                        # all tests
python -m pytest tests/test_server.py  # single file
python -m pytest -k "test_format"      # single test pattern

# Start web dashboard (auto-restarts on crash)
make dashboard

# Run triage manually
make triage MODEL=haiku     # default; also: sonnet, opus
make watch MODEL=haiku      # run every 5 min

# Dashboard PIN management
make set-pin

# Re-link slash commands after editing commands/*.md
make link-commands

# Container
make podman-build
make podman-push

Architecture

MCP Server (gmail_mcp_server/)

  • server.py — GmailMCPServer wraps mcp.server.Server. Maintains an in-memory position map (email_position_map) that maps 1-based integer positions (shown in list_unread_emails output) to Gmail message IDs. This map is rebuilt on every list_unread_emails call, so tools like delete_emails and archive_emails accept positions[] referencing the last fetch. Also holds an in-memory action log (capped at 100).
  • gmail_client.py — GmailClient wraps google-api-python-client. Auth is lazy: _ensure_authenticated() is called before every API call. Token is read from token.json; interactive OAuth only runs when GMAIL_INTERACTIVE_AUTH=1. modify_labels automatically removes all other Triage/* labels when a new one is added — this enforces the one-label-per-email invariant.
  • auth.py — standalone auth helper invoked by make auth.

Read the full file on GitHub · 95 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.

  1. 2mo ago First seen · 95 lines · 1,299 tokens per session scan A 9cfb08231ad5

Subscribe to this mod's changes

gmail-mcp-server GEMINI.md is an instructions file published in the GitHub repository jnpacker/gmail-mcp-server (0 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,299 tokens to every session, about $0.0052 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-server GEMINI.md compared with instructions from other repositories

gmail-mcp-server GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gmail-mcp-server GEMINI.mdjnpacker/gmail-mcp-serverInstructions file018d agoApache-2.0A1,299Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode