Borrowing it
Nothing to install: this file belongs to promobase/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/promobase/google-ads-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/promobase/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/promobase/google-ads-mcp/claude-md)<a href="https://agentmods.dev/instructions/promobase/google-ads-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/promobase/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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
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 8d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
You're working on google-ads-mcp project, it's a MCP(model context protocal) server that wraps the google ads api for LLM's interaction. You will use the tools to search, fetch web page contents to read the docs, and implement.
about google ads api
google ads offers it's own client sdk as well as REST api. Client one has python sdk, built on top of protobuf schema. REST api does not have any existing openapi specs but referenec docs. we decided to go with python sdk, since it's well maintained and does most of the heavy lifting, i.e. retries, pagination, etc.
resources
here are some high level resources:
- read the
./refs/googleads.llms.txtfor resources related to google ads api - use the
./refs/fastmcp.llms.txtfor full list of docs on how mcp server works. - use the cloudflare tools fetch urls via md/html, which is cleaner and easy to digest.
- you have access to
google-ads-pythonwhich contains source code for the python sdk, as well as all the types generated from protocol buffers.
RULES
- we use
uvfor pagkage management, seepyproject.tomlfor details & configs. - after changes run
uv run ruff format .anduv run pyright - Our goal is to provide 1:1 mapping to ALL google ads services, and wrap them to MCP tools for LLMs to interact with. You can use files to help you track progress. use the API reference or the google-ads python codebase to read all the services available, and implement it. For each service, implement tests and make sure they pass. The implementation should be FULLY typed, using generated types from google ads v20 services.
CURRENT TASK
Here is the current task you're working on. Prioritize this over everything else.
We're in the middle of creating MCP tools based on google ads api. We need to ensure 1:1 mapping and fully type safe. You will create a TRACKER.md, list down all the existing services in google-ads-python, and then audit the current progress and mark them. Start with everything as "not impl". Next, we will start one by one.
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.
- 8d ago First seen · 34 lines · 612 tokens per session scan A 1aa3e36f7722
google-ads-mcp CLAUDE.md is an instructions file published in the GitHub repository promobase/google-ads-mcp (22 stars, last pushed 1mo ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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 2026-08-30.
Other instructions, from other repositories
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.
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).
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).
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.
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.