Connects Claude to Google Analytics 4 properties via Pipeworx's gateway. You get four tools: run custom reports with dimensions and metrics, list accessible properties, pull realtime user counts, and fetch metadata to discover available fields. Useful when you need to query GA4 data conversationally instead of clicking through the web UI or writing API calls. The ask_pipeworx wrapper lets you ask analytics questions in plain English and it routes to the right tool automatically. Part of a larger gateway offering 673+ data sources, but works standalone if you only need GA4 access.
Google Analytics MCP Pack
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|---|
ga_run_report | Query GA4 analytics data by dimensions (e.g., "city", "pagePath") and metrics (e.g., "activeUsers", "sessions") for a date range. Returns aggregated data rows with dimension and metric values. |
ga_list_properties | List all GA4 properties you can access. Returns property IDs, names, creation dates, and account info. Use to find the property ID for ga_run_report queries. |
ga_get_realtime | Check live user activity in a GA4 property right now. Returns current active user count and real-time engagement metrics. Specify property ID (e.g., "123456789"). |
ga_get_metadata | Discover available dimensions and metrics for a GA4 property. Returns field names, descriptions, and data types to build accurate ga_run_report queries. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"google_analytics": {
"url": "https://gateway.pipeworx.io/google_analytics/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Google_analytics data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
io.github.infoinlet-marketplace/mcp-observability
betterdb-inc/monitor
com.mcparmory/datadog
thotischner/observability-mcp
io.github.tantiope/datadog-mcp
io.github.us-all/datadog