GoogleAdsMCP CLAUDE.md

A project instruction file describing a Google Ads MCP server, a program that lets an AI assistant access Google Ads through a standard tool interface.

In plain words
What is it for?
Use it as context when developing or maintaining this Python server and its Google Ads tools.
Why use it?
It gives coding agents the project’s architecture, technologies, safety rules, and recurring implementation patterns.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/bertramdev/googleadsmcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/bertramdev/GoogleAdsMCP
Per session 367 This file is loaded in full into every session.
When invoked 367 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00367 $0.00367
Opus 5 $0.00183 $0.00183
Sonnet 5 $0.00073 $0.00073
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash 125c4353705d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

GoogleAdsMCP 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 38 lines

What it actually says

Project Overview

A comprehensive Google Ads MCP server providing ~47 tools across 9 categories for full read/write access to Google Ads accounts via the MCP protocol.

Tech Stack

  • Python 3.12+, uv for dependency management
  • mcp[cli] (FastMCP) for MCP server
  • google-ads Python client library (API v23)
  • Pydantic v2 for config and models
  • pytest for testing

Architecture

  • src/google_ads_mcp/ — main package
  • src/google_ads_mcp/tools/ — tool modules (one per category)
  • Tools return dicts, never raise exceptions (structured error responses)
  • Removal tools (remove_*) require confirm_removal=True parameter; set_*_status tools have no confirmation guard
  • All logging to stderr (stdio transport requirement)
  • json_response=True on FastMCP for LLM-friendly output

Key Patterns

  • sanitize_customer_id() strips dashes: "123-456-7890" → "1234567890"
  • proto_to_dict() converts protobuf objects to dicts
  • Micros conversion: $1.00 = 1,000,000 micros
  • Lifespan pattern for shared GoogleAdsClient instance
  • Tools registered via decorators in tool modules, imported in tools/__init__.py

Commands

  • uv run google-ads-mcp — start server
  • uv run pytest — run tests
  • uv sync — install dependencies

Conventions

  • Conventional commits (feat:, fix:, docs:, etc.)
  • Google-style docstrings
  • Type hints on all public functions
  • Black formatting, isort for imports
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.

  1. 2d ago First seen · 38 lines · 367 tokens per session scan A 125c4353705d

Subscribe to this mod's changes

GoogleAdsMCP CLAUDE.md is an instructions file published in the GitHub repository bertramdev/GoogleAdsMCP (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 367 tokens to every session, about $0.0018 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.