Monitoring query
monitoring_queryRun a PromQL query over a range on a project's monitoring — its Grafana's Prometheus data source (get_monitoring) — as a dashboard does: each series with its labels, min, max, avg, last and its points. At most 31 days, 300 points a series (a step that gives more is widened, and a note says so), 30 series (aggregate with sum by / avg by (host)); points are left out past 2000 in one answer, the summaries still over all of them. 'source' says the Grafana, the data source, when it was asked and the period counted. The labels are the monitoring's own: read them off monitoring_dashboards' queries or monitoring_hosts' before guessing. For the people who work in the project and the company; at most 60 reads of a project's monitoring an hour, agents and people together. A refusal has a 'state': not_connected (with the 'url' of the screen that connects one), off, refused, sealed, unreachable, busy, too_big, missing, no_access, not_found, bad_request.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"project": "<project>",
"promql": "<promql>"
},
"name": "monitoring_query"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | The end of the range, ISO 8601, e.g. '2026-11-20T09:00:00Z'. Default now. | |
| step | No | The step: '30s', '5m', '1h'. Default about 120 points over the range. | |
| range | No | How far back from 'end': '30m', '6h', '1d', '7d'. Default '1h', at most '31d'. | |
| promql | Yes | The PromQL expression, e.g. 'avg by (host) (node_load1)'. | |
| project | Yes | Project key, e.g. 'PM'. |