google-ads-mcp-unofficial: Instructions file for Codex

AGENTS.md

google-ads-mcp-unofficial AGENTS.md is an instructions file for Codex, OpenCode from davidmosiah/google-ads-mcp-unofficial. It costs 851 tokens per session, scanned A, original, MIT.

Instructions for safely operating an unofficial Google Ads MCP server with 22 tools. Google Ads is Google's platform for creating and managing online advertising campaigns; the instructions cover account discovery, reporting, audits, and controlled changes.

In plain words
What is it for?
Use them to check Google Ads access, list accounts, generate performance reports, find wasted spend, and—when explicitly enabled—make carefully confirmed changes.
Why use it?
They provide a defined sequence for checking the connection and account before using advertising data, while keeping changes disabled unless explicitly allowed.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is davidmosiah/google-ads-mcp-unofficial's own configuration. It tells Codex and OpenCode how to work on google-ads-mcp-unofficial itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything google-ads-mcp-unofficial configures →

Reuse

Borrowing it

Nothing to install: this file belongs to davidmosiah/google-ads-mcp-unofficial. 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/davidmosiah/google-ads-mcp-unofficial/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/davidmosiah/google-ads-mcp-unofficial

Made for: Codex, OpenCode.

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.

agentmods badge for google-ads-mcp-unofficial AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/davidmosiah/google-ads-mcp-unofficial/agents-md/github.svg)](https://agentmods.dev/instructions/davidmosiah/google-ads-mcp-unofficial/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/davidmosiah/google-ads-mcp-unofficial/agents-md"><img src="https://agentmods.dev/badge/instructions/davidmosiah/google-ads-mcp-unofficial/agents-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.

agentmods 80×15 button for google-ads-mcp-unofficial AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/davidmosiah/google-ads-mcp-unofficial/agents-md"><img src="https://agentmods.dev/badge/instructions/davidmosiah/google-ads-mcp-unofficial/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 851 This file is loaded in full into every session.
When invoked 851 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00851 $0.00851
Opus 5 $0.00426 $0.00426
Sonnet 5 $0.00170 $0.00170
Haiku 4.5 $0.00085 $0.00085

Measured 10d ago against content hash eba3c11268cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

google-ads-mcp-unofficial AGENTS.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 10d 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.

AGENTS.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-facing usage — google-ads-mcp-unofficial

This document tells AI agents how to operate the Google Ads MCP safely.

Tool count: 22

  • 5 meta/diagnostic — always safe, no API calls
  • 3 shared profile — read/write ~/.delx-wellness/profile.json
  • 3 auth — OAuth lifecycle
  • 8 reads — GAQL queries against Google Ads REST
  • 2 workflow — synthesized reports/audits, always read-only
  • 6 mutations — GATED by GOOGLE_ADS_ALLOW_MUTATIONS

Agent first-call ladder

  1. google_ads_connection_status — verify env + token are ready
  2. google_ads_data_inventory — see categories + tool roster
  3. google_ads_list_accounts — discover the customer_id to operate on
  4. google_ads_daily_report({ customer_id }) — fast performance pulse
  5. google_ads_find_waste({ customer_id }) — identify cleanup candidates (read-only)

Hard rules (do not violate)

  1. Mutations are off by default. Before suggesting the user enable GOOGLE_ADS_ALLOW_MUTATIONS, explicitly ask. Do not silently set it.
  2. One change at a time. When mutations are enabled, do not batch pauses or bid changes across many keywords without explicit confirmation per change.
  3. explicit_user_intent: true is required on every mutation call. Even after env-level enable.
  4. Frame outputs as marketing operations, not financial advice.
  5. Customer ids leak account scale. Default to structured privacy mode (partial-redacted). Use raw only when the user needs the full id.
  6. Daily report is read-only. It synthesizes 3 windows of metrics — never propose actions in the same call.

Money safety

Google Ads spend is real money. The MCP defends against accidental waste with three layers:

  • Env-level gate (GOOGLE_ADS_ALLOW_MUTATIONS)
  • Per-call gate (explicit_user_intent)
  • Audit log (every mutation written to stderr with resource_name + payload)

If a write tool errors with "Write tools are disabled...", do not retry. Surface the message to the user and let them decide whether to enable mutations.

Read the full file on GitHub · 91 lines

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. 10d ago First seen · 91 lines · 851 tokens per session scan A eba3c11268cd

Subscribe to this mod's changes

google-ads-mcp-unofficial AGENTS.md is an instructions file published in the GitHub repository davidmosiah/google-ads-mcp-unofficial (4 stars, last pushed 3d ago), licensed MIT. It adds 851 tokens to every session, about $0.0043 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens