Borrowing it
Nothing to install: this file belongs to WEYERSK/Google-Ads-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/WEYERSK/Google-Ads-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/WEYERSK/Google-Ads-MCPWrote 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/weyersk/google-ads-mcp/claude-md)<a href="https://agentmods.dev/instructions/weyersk/google-ads-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/weyersk/google-ads-mcp/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 5.1 | $0.01461 | $0.01461 |
| Opus 5 | $0.00731 | $0.00731 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
Google-Ads-MCP 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 7d 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 — 68 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 is
A local stdio MCP server (FastMCP + official google-ads Python library) exposing 16 tools for full Google Ads campaign management: 6 GAQL-based read tools and 10 write tools. Every write is gated by a dry-run/confirm safety flow because these tools can spend real ad budget.
Design spec: docs/superpowers/specs/2026-07-07-google-ads-mcp-design.md. The original task-by-task implementation plan was removed once the build was done: its verbatim code snippets had drifted from the shipped code in four reviewed places (enum validation via enums.py, keywords_tools import alias in server.py, type(op)(raw) proto construction in mutate.py, regex-based customer-ID normalisation), so the source is the only authority on implementation detail. The plan remains in git history if it is ever needed.
Commands
All commands run from the repo root using the project venv (Windows paths):
.venv/Scripts/python.exe -m pytest -q # full suite
.venv/Scripts/python.exe -m pytest tests/test_safety.py -v # one file
.venv/Scripts/python.exe -m pytest tests/test_safety.py::test_preview_validates_only_and_returns_token -v # one test
.venv/Scripts/python.exe -m pip install -e ".[dev]" # (re)install editable + dev deps
.venv/Scripts/python.exe -m google_ads_mcp.server # run the MCP server (stdio)
.venv/Scripts/python.exe scripts/generate_refresh_token.py --client-id X --client-secret Y # mint OAuth refresh token
There is no linter configured. Tests must produce pristine output (no warnings).
Architecture
Request flow for a write:
server.py (@mcp.tool wrapper, safe_call)
-> tools/{campaigns,adgroups,ads,keywords,mutate}.py
builds proto operation(s) + a human-readable summary;
calls client.get_client() itself (lazy cached GoogleAdsClient,
fed by config.load_config reading .env) and passes the client into:
-> safety.execute_write(client=..., ...) (preview/commit engine: the core)
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.
- 7d ago First seen · 68 lines · 1,461 tokens per session scan A 9e2ced166796
Google-Ads-MCP CLAUDE.md is an instructions file published in the GitHub repository WEYERSK/Google-Ads-MCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,461 tokens to every session, about $0.0073 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
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.
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).
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.