google-ads-mcp-server

Google Ads MCP Server

Updated on May 22, 2025 - Phase 5 Automated Insights Features Implementation Complete

A Model Context Protocol (MCP) server that provides access to Google Ads data through Claude Desktop.

Features

• Access Google Ads campaigns, accounts, and performance metrics via Claude
• Budget Management API Endpoints with visualizations
• Keyword Management API Endpoints with visualizations
• Ad Group Management API Endpoints
• Support for Manager and client account data
• Built-in caching to improve performance and reduce calls
• Claude Artifacts integration for data visualization
• Multi-environment support (development, testing, production)
• Containerized deployment with Docker

Project Quantum Pulse Roadmap

Phase 1: Ad Group Management API Endpoints (COMPLETE) - March 29 to April 4, 2025

• Get ad groups with filtering capabilities
• View ad group performance metrics
• Create new ad groups
• Update existing ad groups
• Visualize ad group performance

Phase 2: Keyword Management API Endpoints (COMPLETE) - April 5 to April 18, 2025

• Browse keywords with filtering capabilities
• Analyze search terms and find insights
• Add, update, and remove keywords
• Visualize keyword performance

Phase 3: Budget Management API Endpoints (COMPLETE) - April 19 to May 2, 2025

• Retrieve campaign budgets with performance metrics
• Analyze budget utilization and distribution
• Generate budget recommendations
• Visualize budget performance

Phase 4: Enhanced Visualization Templates (COMPLETE) - May 3 to May 16, 2025

• Implement comprehensive dashboard templates
• Create comparison visualization templates
• Build breakdown visualization templates

Phase 5: Automated Insights Features (COMPLETE) - May 17 to May 30, 2025

• Implement performance anomaly detection
• Generate optimization suggestions
• Discover growth opportunities
• Create integrated insights dashboard

Prerequisites

• Python 3.9 or higher
• Google Ads API credentials
• Claude Desktop

Quick Start

Local Development

1. Clone the repository
2. Set up a virtual environment
3. Install dependencies
4. Create a .env file with your Google Ads credentials
5. Run the server

Docker Deployment

1. Build the Docker image
2. Run the container

Configuration

• Supports different environments with environment-specific configurations.

Claude Desktop Integration

1. Configure Claude Desktop for the MCP server.
2. Restart Claude Desktop and use Google Ads data by asking questions.

Ad Group Management Tools

MCP tools available for ad group management:

• Get ad groups with filtering
• Get ad group performance metrics
• Create and update ad groups

Keyword Management Tools

MCP tools available for keyword management:

• Get keywords with filtering
• Add, update, and remove keywords
• Analyze search terms

Budget Management Tools

MCP tools available for budget management:

• Get campaign budgets
• Analyze budget utilization
• Update budget properties

Enhanced Visualization Tools

Visualization tools include dashboard, comparison, and breakdown tools.

Automated Insights Tools

Includes anomaly detection, optimization suggestions, opportunity discovery, and integrated insights tool.

Deployment

Includes Kubernetes manifests and CI/CD pipelines.

Security

• Credentials stored in Kubernetes secrets
• Proper authentication and rate limiting
• Container security best practices

Testing

Run the test suite with pytest and other specific tests.

Contributing

1. Fork the repository
2. Create a feature branch
3. Commit changes
4. Push to the branch
5. Submit a pull request

License

Licensed under the MIT License.

Acknowledgements

Thanks to Google Ads API and Anthropic.