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/ngs/google-mcp-server/claude-mdgit clone --depth 1 https://github.com/ngs/google-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/ngs/google-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/ngs/google-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ngs/google-mcp-server/claude-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 | $0.02141 | $0.02141 |
| Opus 5 | $0.01071 | $0.01071 |
| Sonnet 5 | $0.00428 | $0.00428 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
google-mcp-server 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 4d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Instructions for Google MCP Server
This document contains specific instructions for Claude Code when working with the Google MCP Server project.
Project Overview
This is a Go-based MCP (Model Context Protocol) server that integrates with Google APIs including Calendar, Drive, Gmail, Sheets, and Docs. The server uses OAuth 2.0 for authentication and provides tools and resources accessible through MCP-compatible clients.
Development Guidelines
Important Rules
- NEVER create test scripts or demo scripts - Testing should be done through the MCP interface or existing tools
- DO NOT create standalone test programs - Use the MCP server directly for testing functionality
- AVOID creating example/demo files - The MCP server itself is the interface for testing
- NEVER write Go programs to call Google APIs directly - Always use MCP tools or existing server functionality
- DO NOT create any executable programs - If MCP tools are unavailable, investigate why and report the issue instead
Code Style
- Use Go idioms and best practices
- Follow the existing code structure and patterns
- Keep functions focused and single-purpose
- Use meaningful variable and function names
- Add error handling for all API calls
Testing
Before committing any changes, always run:
go test ./...
go fmt ./...
Building
To build the project:
go build -o google-mcp-server .
Service Implementation Status
Fully Implemented with Multi-Account Support
- Calendar Service (
calendar/): All 8 tools + multi-account support viacalendar/multi_account.go - Drive Service (
drive/): All 19 tools including Markdown support + multi-account support viadrive/multi_account.go - Gmail Service (
gmail/): 3 core tools + multi-account support viagmail/multi_account.go - Account Management (
accounts/): 5 tools for managing multiple Google accounts
Basic Implementation
- Sheets Service (
sheets/): 12 tools (spreadsheet create/get, values get/update/append/clear, sheet duplicate/add/delete/update, dimension insert/delete) + multi-account support viasheets/multi_account.go - Docs Service (
docs/): 3 basic tools (get/create/update documents)
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.
- 4d ago First seen · 245 lines · 2,141 tokens per session scan A 3a7e1353a010
google-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ngs/google-mcp-server (2 stars, last pushed 12d ago), licensed MIT. It adds 2,141 tokens to every session, about $0.0107 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
gmail-mcp-server CLAUDE.md
Instructions for ihiteshgupta/gmail-mcp-server, covering gmail mcp server, tech stack, available tools (19 total), email operations and drafts.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.