Agent session usage
livekit_agent_observability|Agent session usage|unknown|minute
mcp · handle livekit_agent_observability · source page
livekit_agent_observability|Agent session usage|unknown|minute
livekit_agent_observability|Build|free|flat
livekit_agent_observability|Scale|team_sme|flat
livekit_agent_observability|Ship|pro|flat
Canvas Agent · job 76%Delx MCP Server · job 79%yc_plum_hackathon_mcp · job 75%appsignal_mcp · job 72%Chamade · job 79%callsyncapp · job 74%lastping · job 79%transcription · job 78%kaicalls · job 74%logaflow_mcp_server · job 74%luciq · job 72%storyflo · job 74%monte_carlo · job 81%dynatrace_mcp_server · job 78%telnyx · job 73%usertold · job 73%singchat · job 76%KEEPitALIVE MCP · job 76%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series