Collapse navigation tree

Collapse

Monitor MCP Server Activity

Monitor MCP server activity using OpenTelemetry traces emitted to the redpanda.otel_traces topic.

After reading this page, you will be able to:

  • Consume traces from the redpanda.otel_traces topic

  • Track tool invocations and measure performance

  • Debug tool failures using trace data

For conceptual background on traces, spans, and the trace data structure, see Transcripts and AI Observability.

Prerequisites

You must have an existing MCP server. If you do not have one, see Remote MCP Server Quickstart.

View transcripts in the Cloud Console

  1. Click Transcripts.

  2. Select a recent transcript from your MCP server tool invocations.

The transcripts view displays:

  • Timeline: Visual history of recent executions with success/error indicators

  • Trace list: Hierarchical view of traces and spans

  • Summary panel: Detailed metrics when you select a transcript

Timeline visualization

The timeline shows execution patterns over time:

  • Green bars: Successful executions

  • Red bars: Failed executions with errors

  • Gray bars: Incomplete traces or traces still loading

  • Time range: Displays the last few hours by default

Use the timeline to spot patterns like error clusters, performance degradation over time, or gaps indicating downtime.

Trace hierarchy

The trace list shows nested operations with visual duration bars indicating how long each operation took. Click the expand arrows (▶) to drill into nested spans and see the complete execution flow.

For details on span types, see MCP server trace hierarchy.

Summary panel

When you select a transcript, the summary panel shows:

  • Duration: Total execution time for this request

  • Total Spans: Number of operations in the trace

  • Service: The MCP server identifier

Analyze traces programmatically

MCP servers emit OpenTelemetry traces to the redpanda.otel_traces topic. Consume these traces to build custom monitoring, track tool usage, and analyze performance.

Consume traces

  • Cloud Console

  • rpk

  • Data Plane API

  1. In the Redpanda Cloud Console, navigate to Topics.

  2. Select redpanda.otel_traces.

  3. Click Messages to view recent traces.

  4. Use filters to search for specific trace IDs, span names, or time ranges.

Consume the most recent traces:

rpk topic consume redpanda.otel_traces --offset end -n 10

Filter for specific MCP server activity by examining the span attributes.

Use the Data Plane API to programmatically consume traces and integrate with your monitoring pipeline.

Track tool invocations

Monitor which tools are being called and how often by filtering spans where instrumentationScope.name is rpcn-mcp. The name field shows which tool was invoked.

Example: Find all invocations of a specific tool:

rpk topic consume redpanda.otel_traces --offset start \
  | jq '.value | select(.instrumentationScope.name == "rpcn-mcp" and .name == "weather")'

Measure performance

Calculate tool execution time using span timestamps:

Duration (ms) = (endTimeUnixNano - startTimeUnixNano) / 1000000

Track percentiles (p50, p95, p99) to identify performance issues and set alerts for durations exceeding acceptable thresholds.

Debug failures

Filter for error spans where status.code is 2:

rpk topic consume redpanda.otel_traces --offset start \
  | jq '.value | select(.status.code == 2)'

Check status.message for error details and the events array for error events with timestamps. Use traceId to correlate related spans across the distributed system.

Next steps