google-ads-mcp

google-ads-mcp is a skill for Claude Code from itallstartedwithaidea/google-ads-skills. It costs 66 tokens per session (1,315 once invoked), scanned A, original, Apache-2.0.

Instructions for connecting Claude or another MCP client to Google Ads, Google's service for managing and querying online advertising campaigns.

In plain words
What is it for?
Use it to configure live Google Ads API access through an MCP server and query an authorised Google Ads account.
Why use it?
It removes the guesswork around installing the server, supplying Google Ads credentials, configuring the connection, and diagnosing setup problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the google-ads-full plugin — 5 skills shipped together

Good fit Use it to configure live Google Ads API access through an MCP server and query an authorised Google Ads account.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itallstartedwithaidea/google-ads-skills/google-ads-mcp
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.

Any agent
npx skills add itallstartedwithaidea/google-ads-skills --skill google-ads-mcp
Clone the repo
git clone --depth 1 https://github.com/itallstartedwithaidea/google-ads-skills

Made for: Claude Code.

Or install google-ads-full, the plugin that ships this one along with the rest of its 5 skills.

Its marketplace also offers this one on its own, as the plugin google-ads-mcp-only/plugin install google-ads-mcp-only after adding the marketplace above.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/itallstartedwithaidea/google-ads-skills/google-ads-mcp"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/google-ads-skills/google-ads-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,315 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00066 $0.01315
Opus 5 $0.00033 $0.00658
Sonnet 5 $0.00013 $0.00263
Haiku 4.5 $0.00007 $0.00131

Measured 10d ago against content hash 3e04c777c718, 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 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.

skills/google-ads-mcp/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill configures the google-ads-mcp server for live Google Ads API access through Claude Code, Claude Desktop, Cursor, or any MCP client.

Quick Setup

1. Install

pip install git+https://github.com/itallstartedwithaidea/google-ads-mcp.git

2. Configure Credentials

Create a .env file or set environment variables:

GOOGLE_ADS_DEVELOPER_TOKEN=your-developer-token
GOOGLE_ADS_CLIENT_ID=your-oauth-client-id
GOOGLE_ADS_CLIENT_SECRET=your-oauth-client-secret
GOOGLE_ADS_REFRESH_TOKEN=your-refresh-token
GOOGLE_ADS_LOGIN_CUSTOMER_ID=123-456-7890

Or point to an existing google-ads.yaml:

GOOGLE_ADS_CREDENTIALS=/path/to/google-ads.yaml
GOOGLE_ADS_LOGIN_CUSTOMER_ID=123-456-7890

3. Run

python -m ads_mcp.server

Claude Code Configuration

Place .mcp.json in your project root:

{
  "mcpServers": {
    "google-ads": {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "ads_mcp.server"],
      "env": {
        "GOOGLE_ADS_CREDENTIALS": "${GOOGLE_ADS_CREDENTIALS}",
        "GOOGLE_ADS_LOGIN_CUSTOMER_ID": "${GOOGLE_ADS_LOGIN_CUSTOMER_ID}"
      }
    }
  }
}

Claude Code auto-discovers .mcp.json and loads the server on startup.

Claude Desktop Configuration

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "google-ads": {
      "command": "python",
      "args": ["-m", "ads_mcp.server"],
      "env": {
        "GOOGLE_ADS_CREDENTIALS": "/path/to/google-ads.yaml",
        "GOOGLE_ADS_LOGIN_CUSTOMER_ID": "123-456-7890"
      }
    }
  }
}

Available Tools (29)

Read Tools (9)

Tool Description
list_accessible_customers List all accessible customer accounts
list_accounts List accounts under an MCC with details
execute_gaql Run custom GAQL queries
get_campaign_performance Campaign metrics with date range
get_keyword_performance Keyword metrics and quality scores
get_search_terms Search term report with wasted spend
get_ad_performance Ad creative performance
get_account_budget_summary Budget utilization analysis
generate_keyword_ideas Keyword Planner search volume and CPC

Read the full file on GitHub · 165 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 · 165 lines · 66 tokens per session scan A 3e04c777c718

Subscribe to this mod's changes

google-ads-mcp is a skill published in the GitHub repository itallstartedwithaidea/google-ads-skills (34 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,315 once invoked, about $0.0003 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.