Search spans and slow routes
search_tracesWith no filters: every route and screen with its count, error rate, p50, p95 and slowest dependency. With any filter: matching spans from the backend and the app, or count, avg, p50, p95 and errors with group_by. Use it to find what is slow or failing, then open one with get_trace. Spans are kept 30 days.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "search_traces"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Text in the span name, any case | |
| op | No | Like http.server, http.client, ui.load, app.start, gen_ai, mcp.server | |
| to | No | An ISO time, or how long ago | |
| from | No | An ISO time, or 30m, 24h, 7d (default 24h) | |
| sort | No | For spans (default recent) | |
| limit | No | Rows (default 50, overview 25) | |
| range | No | Window of the routes overview (default 24h) | |
| route | No | ||
| cursor | No | next_cursor from the last answer | |
| source | No | Default all | |
| status | No | ok, error, or one HTTP status like 503 | |
| release | No | Only this release: 2.0.77+185, 2.0.77 (every build) or package@2.0.77+185 | |
| service | No | ||
| group_by | No | Counts and timings per value instead of spans. release and environment also give p75, p90, p99 and time spent | |
| timeseries | No | true: points over time instead of rows (per minute, error rate, p50, p95), with where releases started | |
| environment | No | Only this environment, like production ('all' for every one) | |
| min_duration_ms | No |