Google Ads Library MCP

🚀 Google Ads Library MCP Server

A Model Context Protocol (MCP) server for the Google Ads Transparency Center, enabling users to search, analyze, and gain insights from Google's public ads transparency data.

🚀 Quick Start

This MCP server allows you to search Google's public ads transparency center for any company or brand, view their current ads, and conduct in - depth advertising analysis. You can analyze ad images and text, gain comprehensive insights from video ads, compare companies' advertising strategies, and understand what works in their campaigns. Here's an example of its capabilities when connected to Claude:

Example Link

To get updates on this and other projects we work on subscribe here

PS: Join our Twitter community for all things MCP

💻 Usage Examples

Basic Usage

Here are some example prompts to get you started:

How many ads is 'AnthropicAI' running? What's their split across video and image?

What messaging is 'AnthropicAI' running right now in their ads?

Analyze the video ads from 'Nike' and extract their visual storytelling strategy, pacing, and brand messaging techniques.

Do a deep comparison to the messaging between 'AnthropicAI', 'Perplexity AI' and 'OpenAI'. Give it a nice forwardable summary.

📦 Installation

Prerequisites

• Python 3.12+
• Anthropic Claude Desktop app (or Cursor)
• Pip (Python package manager), install with python -m pip install
• An access token for Scrape Creators
• A Google Gemini API key for video analysis (optional, only needed for video ads)

Quick Install (Recommended)

1. Clone and run the install script

   git clone https://github.com/trypeggy/google-ads-library-mcp.git
   cd google-ads-library-mcp
   
   # For macOS/Linux:
   ./install.sh
   
   # For Windows:
   install.bat
   

2. Configure your API keys Edit the .env file that was created and add your API keys:
   • Get your ScrapeCreators API key at scrapecreators.com
   • Get your Gemini API key at Google AI Studio (optional, for video analysis)

Manual Install

1. Clone this repository

   git clone https://github.com/trypeggy/google-ads-library-mcp.git
   cd google-ads-library-mcp
   

2. Install dependencies

   pip install -r requirements.txt
   

3. Configure API keys Copy the template and configure your API keys:

   cp .env.template .env
   # Then edit .env with your actual API keys
   

   To obtain API keys:
   • Sign up for Scrape Creators here
   • Get a Google Gemini API key here (optional, for video analysis)
4. Connect to the MCP server Add the MCP server configuration to your Claude Desktop or Cursor config:

   {
     "mcpServers": {
       "google_ad_library": {
       "command": "/usr/local/opt/python@3.13/bin/python3",
         "args": [
           "{{PATH_TO_PROJECT}}/google-ads-library-mcp/mcp_server.py"
         ]
       }
     }
   }
   

   Replace {{PATH_TO_PROJECT}} with the full path to where you cloned this repository. Note: API keys are automatically loaded from the .env file. Command line arguments are still supported and take priority over environment variables if provided. For Claude Desktop: Save this as claude_desktop_config.json in your Claude Desktop configuration directory at:

   ~/Library/Application Support/Claude/claude_desktop_config.json
   

   For Cursor: Save this as mcp.json in your Cursor configuration directory at:

   ~/.cursor/mcp.json
   

5. Restart Claude Desktop / Cursor Open Claude Desktop and you should now see the Google Ads Library as an available integration. Or restart Cursor.

🔧 Technical Details

1. Claude sends requests to the Python MCP server
2. The MCP server queries the ScrapeCreators API for Google Ads Transparency Center data
3. Data flows back through the chain to Claude

Google Ads

This server connects to Google's Ads Transparency Center:

• Google Ads: Uses company domain (e.g., "nike.com") or advertiser ID for search
• Response Format: Returns ads with format types (text/image/video) and detailed variations
• Ad Details: Each ad can have multiple variations with different headlines and descriptions
• Regional Data: Includes region - specific statistics and impression data

Tips:

• Use company domains (e.g., "nike.com") instead of brand names for searching
• Text ads are now supported in addition to image and video ads
• Each ad may have multiple variations with different headlines and descriptions

Available MCP Tools

🛠️ Troubleshooting

Common Issues

⚠️ Important Note

API Key Not Found Error:

• Ensure your .env file is in the project root directory
• If you don't have a .env file, copy it from the template: cp .env.template .env
• Check that your API keys are correctly formatted without quotes
• Verify the .env file contains SCRAPECREATORS_API_KEY=your_key_here
• For video analysis, ensure GEMINI_API_KEY=your_key_here is also added

Video Analysis Not Working:

• Confirm you have a valid Google Gemini API key in your .env file
• Video analysis requires the GEMINI_API_KEY environment variable

MCP Server Connection Issues:

• Verify the path in your MCP configuration points to the correct location
• Make sure you've installed all dependencies with pip install -r requirements.txt
• Restart Claude Desktop/Cursor after configuration changes

For additional Claude Desktop integration troubleshooting, see the MCP documentation. The documentation includes helpful tips for checking logs and resolving common issues.

💡 Usage Tip

• Use company domains (e.g., "nike.com") instead of brand names for searching
• Text ads are now supported in addition to image and video ads
• Each ad may have multiple variations with different headlines and descriptions

💬 Feedback

Your feedback will be massively appreciated. Please tell us which features on that list you like to see next or request entirely new ones.

📄 License

This project is licensed under the MIT License.