How proxy-intell/google-ads-library-mcp works
This is a self-hostable MCP server for searching Google Ads Transparency Center ads and analyzing their images and videos. The principal workflow is an MCP client request, handled by the Python server, which retrieves ads or ad details through ScrapeCreators and returns structured results. Image and video analysis add media caching; video analysis can also use Gemini. Cache statistics, search, and cleanup are separate user-facing capabilities. The Node launcher is a thin runtime entry point. Relationships reflect the excerpts and README; unsampled tool wiring is not inferred.
Main entry points: mcp_server.py MCP Server · media_cache_service.py Media Cache Service · index.js Node Launcher · scrapecreators_service.py Ads API Service
Components 12
MCP Runtime
- Node Launcher
index.js - MCP Server
mcp_server.py
Ad Retrieval
- Ad Tools
mcp_server.py - Ads API Service
src/services/scrapecreators_service.py - ScrapeCreators API
Media Analysis
- Image Analysis
mcp_server.py - Video Analysis
mcp_server.py - Gemini Video AI
Media Cache
- Cache Tools
mcp_server.py - Media Cache Service
src/services/media_cache_service.py - Media Cache
src/services/media_cache_service.py
Other components
- MCP Client
Connections 14
- MCP Client → Node Launcher: starts server
readme.md - Node Launcher → MCP Server: spawns Python
index.js - MCP Client → MCP Server: sends MCP requests
readme.md - MCP Server → Ad Tools: dispatches tools
mcp_server.py - Ad Tools → Ads API Service: requests ads
mcp_server.py - Ads API Service → ScrapeCreators API: fetches ad data
src/services/scrapecreators_service.py - MCP Server → Image Analysis: dispatches tools
mcp_server.py - Image Analysis → Media Cache Service: checks and stores
mcp_server.py - MCP Server → Video Analysis: dispatches tools
mcp_server.py - Video Analysis → Media Cache Service: checks and stores
mcp_server.py - Video Analysis → Gemini Video AI: uploads and analyzes
mcp_server.py - MCP Server → Cache Tools: dispatches tools
mcp_server.py - Cache Tools → Media Cache Service: manages cache
mcp_server.py - Media Cache Service → Media Cache: reads and writes
src/services/media_cache_service.py