What is mcp-gads CLAUDE.md?

Project instructions for building and testing a Google Ads MCP server, a local service that lets an AI agent work with Google Ads data. They describe its commands, response format, API version, and production setup.

Use it when developing, testing, or validating the mcp-gads package, including its Google Ads API calls and production connection.

It gives the coding agent the project’s conventions and checks, reducing guesswork when changing or testing the server.

How pijusz/mcp-gads configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pijusz/mcp-gads. 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/pijusz/mcp-gads/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pijusz/mcp-gads

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/pijusz/mcp-gads/claude-md/github.svg)](https://agentmods.dev/instructions/pijusz/mcp-gads/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pijusz/mcp-gads/claude-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-gads/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/pijusz/mcp-gads/claude-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-gads/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 398 This file is loaded in full into every session.

When invoked 398 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	$0.00398	$0.00398
Opus 5.5	$0.00159	$0.00159
Sonnet 5.5	$0.00080	$0.00080
Haiku 4.5	$0.00040	$0.00040

Measured 14d ago against content hash 0c723682fd9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-gads 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 14d 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 · 37 lines

What it actually says

mcp-gads

Google Ads MCP server in Bun/TypeScript. See AGENTS.md for detailed guidelines.

Quick reference

Runtime: Bun (dev) / Node (built)
Entry: src/index.ts
Build: bun run build → mcp-gads (standalone binary), bun run build:npm → dist/index.js
Test: bun test
API version: v26 (Google Ads REST API)

Key patterns

All tools return { content: [{ type: "text", text }] } — MCP tool response format
fetchWithRetry in services/google-ads-api.ts handles 429/5xx with exponential backoff
Date filters use buildDateFilter(days) which falls back to BETWEEN for non-standard day counts
Mutation tools are gated by GOOGLE_ADS_ENABLE_MUTATIONS=true env var

Prod testing (published package)

Use the published package for production validation:

claude mcp add gads --scope user --transport stdio \
  -e GOOGLE_ADS_DEVELOPER_TOKEN=... \
  -e GOOGLE_ADS_CREDENTIALS_PATH=/abs/path/to/token-or-client.json \
  -- npx -y mcp-gads@latest

If you see handshaking ... connection closed: initialize response, the process is exiting before MCP init. Check these first:

npx -y mcp-gads@latest --version works (npm registry reachable).
GOOGLE_ADS_DEVELOPER_TOKEN is set in MCP env.
GOOGLE_ADS_CREDENTIALS_PATH exists and is readable.
For OAuth client JSON, companion token file exists (*_token.json) or run npx -y mcp-gads@latest setup.

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.

14d ago Changed 0c723682fd9a
2mo ago First seen · 37 lines · 398 tokens per session scan A f606da8e07bd

Subscribe to this mod's changes

mcp-gads CLAUDE.md is an instructions file published in the GitHub repository pijusz/mcp-gads (1 stars, last pushed 15d ago), licensed MIT. It adds 398 tokens to every session, about $0.0016 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.

Marketing and SEO

mcp-gads CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-gads CLAUDE.mdpijusz/mcp-gads	Instructions file	1	15d ago	MIT	A	398	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-gads: Instructions file for Claude Code