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.
npx agentmods add instructions/neutral-stage/gmail-mcp-server/agents-mdgit clone --depth 1 https://github.com/neutral-Stage/gmail-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/neutral-stage/gmail-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/neutral-stage/gmail-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/neutral-stage/gmail-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01398 | $0.01398 |
| Opus 5 | $0.00699 | $0.00699 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
gmail-mcp-server AGENTS.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidelines for AI coding agents working in this Gmail MCP server codebase.
Project Overview
A minimal Gmail MCP (Model Context Protocol) server that enables AI agents to interact with Gmail. Built with TypeScript and Node.js, using the official Gmail API.
Build/Lint/Test Commands
# Install dependencies
npm install
# Build TypeScript to dist/
npm run build
# Run the compiled server
npm start
# Build and run in one command (development)
npm run dev
# Run OAuth authentication flow
npm run auth
Note: This project currently has no automated test suite or linting commands configured. Consider adding tests before making significant changes.
Code Style Guidelines
TypeScript Configuration
- Target: ES2022
- Module: NodeNext (ESM with Node.js resolution)
- Strict mode: enabled
- Output directory:
dist/ - Source directory:
src/
Imports
// Prefer ESM imports with .js extension for local files
import { something } from "./module.js";
// External imports: organize by scope (SDK, then external libs, then Node builtins)
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { OAuth2Client } from "google-auth-library";
import { google } from "googleapis";
import { readFileSync } from "fs";
- Use explicit
.jsextensions in import paths for ESM compatibility - Group imports logically: external packages first, then Node builtins
- Destructure named imports rather than importing entire modules when possible
Formatting
- 2-space indentation
- No semicolons required (TypeScript/ESM handles ASI)
- Max line length: ~100 characters
- Use double quotes for strings consistently
- Trailing commas in multi-line objects/arrays
Types
- Prefer explicit types for function parameters and return values
- Use interfaces for object shapes that are reused
- Avoid
any; useunknownwhen type is uncertain - Leverage Zod schemas for runtime validation and type inference
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.
- 3d ago First seen · 196 lines · 1,398 tokens per session scan A c15ad58f0875
gmail-mcp-server AGENTS.md is an instructions file published in the GitHub repository neutral-Stage/gmail-mcp-server (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,398 tokens to every session, about $0.0070 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.
Other instructions, from other repositories
google-mcp CLAUDE.md
Instructions for quinnjr/google-mcp, covering claude.md, commands, architecture, entry & server and auth.
gmail-mcp AGENTS.md
Instructions for klodr/gmail-mcp, covering agents.md, audience boundary, setup, build, test, lint, typecheck and code style.
gmail-mcp copilot-instructions.md
Instructions for klodr/gmail-mcp: Canonical agent instructions for this repository: read AGENTS.md at the root before generating or editing code.
gmail-mcp CLAUDE.md
Instructions for klodr/gmail-mcp: The canonical agent instructions for this repository live in AGENTS.md at the root. Read AGENTS.md before any code change in this project.
mcp-server-gmail CLAUDE.md
Claude Code instructions for franciscpd/mcp-server-gmail, covering claude.md, .planning/ — single source of truth, workflow — follow this order exactly, phase 1 — discuss and phase 2 — brainstorm.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.