Google Ads MCP
@cohnen
About Google Ads MCP
An MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analytics, and ad management—all th
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"googleAdsServer": {
"command": "/Users/cohnen/dev/mcp-google-ads/.venv/bin/python",
"args": [
"/Users/cohnen/dev/mcp-google-ads/google_ads_server.py"
],
"env": {
"GOOGLE_ADS_CREDENTIALS_PATH": "/Users/cohnen/dev/mcp-google-ads/google_ads_token.json",
"GOOGLE_ADS_DEVELOPER_TOKEN": "<GOOGLE_ADS_DEVELOPER_TOKEN>",
"GOOGLE_ADS_LOGIN_CUSTOMER_ID": "",
"GOOGLE_ADS_CLIENT_ID": "<GOOGLE_ADS_CLIENT_ID>",
"GOOGLE_ADS_CLIENT_SECRET": "<GOOGLE_ADS_CLIENT_SECRET>"
}
}
}
}Tools
5Shows all your Google Ads accounts
Runs a Google Ads Query Language query
Shows campaign metrics with performance data
Detailed analysis of your ad creative performance
Runs any arbitrary GAQL query with formatting options
Overview
What is Google Ads MCP?
A tool that connects Google Ads data with Claude AI, enabling analysis of advertising data through natural language conversations. It provides access to campaign information, performance metrics, keyword analytics, and ad management for advertising professionals.
How to use Google Ads MCP?
Set up Google Ads API access (OAuth 2.0 or Service Account), obtain a developer token, install Python 3.11+, Node.js, and Claude Desktop. Download the repository, create a virtual environment, install dependencies, and configure a .env file with your credentials. Then ask Claude to use tools like list_accounts, execute_gaql_query, get_campaign_performance, get_ad_performance, or run_gaql.
Key features of Google Ads MCP
- View all Google Ads accounts and campaign information.
- Track impressions, clicks, conversions, and cost metrics.
- Identify top and underperforming keywords.
- Analyze ad copy effectiveness and quality scores.
- Monitor campaign budgets and bid strategies.
- Run custom GAQL queries with flexible formatting options.
Use cases of Google Ads MCP
- An advertising manager asks Claude to show which campaigns are performing best this month.
- A marketer analyzes keyword quality scores to optimize ad copy.
- A budget owner monitors spending and gets recommendations for reallocation.
- An analyst runs a custom GAQL query to compare conversion trends across periods.
FAQ from Google Ads MCP
What authentication methods does Google Ads MCP support?
OAuth 2.0 Client ID for user-level access (desktop apps) and Service Account for server-to-server, automated workflows.
Is the Login Customer ID required?
It is optional. Use it when working with a Google Ads Manager Account (MCC) to access multiple client accounts. Skip if accessing a single account directly.
How do I get a Google Ads API Developer Token?
Sign in to your Google Ads account, go to Tools & Settings > Setup > API Center, accept terms, apply for a token, and wait for approval (usually 1–3 business days).
What are the runtime requirements?
Python 3.11 or newer, Node.js, and the Claude Desktop application. The mcp package and other dependencies listed in requirements.txt must be installed.
Can I run custom queries?
Yes, the run_gaql tool lets you execute any arbitrary Google Ads Query Language (GAQL) query with formatting options (table, JSON, or CSV).
Frequently asked questions
What authentication methods does Google Ads MCP support?
OAuth 2.0 Client ID for user-level access (desktop apps) and Service Account for server-to-server, automated workflows.
Is the Login Customer ID required?
It is optional. Use it when working with a Google Ads Manager Account (MCC) to access multiple client accounts. Skip if accessing a single account directly.
How do I get a Google Ads API Developer Token?
Sign in to your Google Ads account, go to Tools & Settings > Setup > API Center, accept terms, apply for a token, and wait for approval (usually 1–3 business days).
What are the runtime requirements?
Python 3.11 or newer, Node.js, and the Claude Desktop application. The mcp package and other dependencies listed in requirements.txt must be installed.
Can I run custom queries?
Yes, the `run_gaql` tool lets you execute any arbitrary Google Ads Query Language (GAQL) query with formatting options (table, JSON, or CSV).
Basic information
More Data & Analytics MCP servers

AskRentAI
AskRentAIAsk your Rent Manager property portfolio anything, from the AI you already use. AskRentAI is a hosted, read-only MCP server for Rent Manager, the property management platform used across a large share of US rental housi

Subtext
Subtext by FullstorySession replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can
Sugra API MCP
Sugra Systems, Inc.Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl
BidSkim - UK Tenders & Contract Renewals
BidSkimUK procurement intelligence for AI assistants: search live UK government tenders, find contract renewals with expiry dates and incumbent suppliers, and profile public-sector buyers and suppliers. Covers Find a Tender, Co

Context.dev
Yahia BakourContext.dev is the web-data infrastructure for AI products and agents, one API that turns the web into clean, structured, LLM-ready data. MCP available at https://mcp.context.dev.
Comments