Skip to main content
You can track MCP server usage using metrics exposed by the API gateway. The Lucidworks team provides a ready-made Grafana dashboard to visualize MCP request volume, latency, and error rates.
New to Lucidworks MCP? See the MCP Server overview for setup instructions and configuration details.

​
How MCP usage is measured

All MCP traffic enters Lucidworks Search through the API gateway at the /mcp route. The gateway isolates MCP traffic from all other gateway routes, providing a clean MCP-only view without touching the MCP server itself.

​
Dashboard overview

The Lucidworks team configures Grafana dashboards for your Lucidworks Search environment. Contact your Lucidworks representative for dashboard access and customization options. The MCP monitoring dashboard includes panels organized into three sections: overview metrics, latency analysis, and traffic breakdown.
Imported Grafana dashboard showing MCP server usage metrics
The MCP Latency Percentiles panel is empty by design. Lucidworks Search’s managed Prometheus does not retain the histogram data required to calculate percentiles, so use Avg Latency to monitor MCP response times.

​
Overview metrics

​
Latency metrics

​
Traffic metrics and errors

​
Notes

  • This dashboard measures MCP usage at the gateway, which is the cleanest signal for request volume, status, and latency. It does not break usage down per MCP tool (such as Search_documents, Get_document) — that would require additional instrumentation in the MCP server.
  • The underlying gateway metrics available on Lucidworks Search do not include the histogram buckets latency percentiles require, which is why that panel is empty (see the note above).