MCP Catalogs
Homemcp-google-ads screenshot

mcp-google-ads

by cohnen·609·Score 48

A Python MCP server that bridges Google Ads with Claude AI for natural language advertising data analysis and management.

financeproductivityai-llm
138
Forks
12
Open issues
7 mo ago
Last commit
2d ago
Indexed

Overview

The Google Ads MCP server provides a comprehensive interface for advertising professionals to analyze and manage their Google Ads campaigns through natural language interactions. It exposes multiple tools for account management, campaign analytics, keyword performance tracking, and budget management. The server supports both OAuth 2.0 and service account authentication methods, with automatic token refreshing capabilities.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Analyze campaign performance metrics through natural language queries
you:Generate visual reports of advertising data with Claude
you:Optimize ad budgets and bid strategies based on performance insights
you:Which authentication method should I use?
you:How long does it take to get a Google Ads API developer token?

When to choose this

Choose this if you're managing Google Ads campaigns and want to analyze performance data through natural language conversations with AI assistants.

When NOT to choose this

Avoid this if you need to manage advertising campaigns on platforms other than Google Ads, or if you prefer not to set up API authentication for Google services.

Tools this server exposes

5 tools extracted from the README
  • list_accounts

    Shows all your Google Ads accounts

  • execute_gaql_query

    Runs a Google Ads Query Language query

  • get_campaign_performance

    Shows campaign metrics with performance data

  • get_ad_performance

    Detailed analysis of your ad creative performance

  • run_gaql

    Runs any arbitrary GAQL query with formatting options

Comparable tools

mcp-facebook-adsmcp-bing-adsgoogle-ads-api-pythongoogle-ads-ruby

Installation

  1. Clone the repository: git clone https://github.com/ixigo/mcp-google-ads.git
  2. Set up Google Ads API credentials (OAuth or Service Account)
  3. Create a virtual environment: uv venv .venv
  4. Activate the environment: source .venv/bin/activate
  5. Install dependencies: uv pip install -r requirements.txt
  6. Configure your .env file with credentials
  7. Add to Claude Desktop config:
{
  "mcpServers": {
    "google-ads": {
      "command": "python",
      "args": ["-m", "mcp_google_ads.server"],
      "env": {
        "GOOGLE_ADS_DEVELOPER_TOKEN": "your-token",
        "GOOGLE_ADS_CLIENT_ID": "your-client-id",
        "GOOGLE_ADS_CLIENT_SECRET": "your-client-secret",
        "GOOGLE_ADS_REFRESH_TOKEN": "your-refresh-token",
        "GOOGLE_ADS_LOGIN_CUSTOMER_ID": "your-id"
      }
    }
  }
}

FAQ

Which authentication method should I use?
Choose OAuth 2.0 for individual users or desktop apps where users need to grant access. Choose service accounts for automated systems or managing multiple accounts programmatically.
How long does it take to get a Google Ads API developer token?
Usually 1-3 business days after submitting your application. Initially you'll get a test token with limitations, which can later be upgraded to a production token.

Compare mcp-google-ads with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.