Terminal
Terminal/Skill
Query aggregated monitor statistics (up/down/paused counts, uptime percentage) and per-monitor response-time time series.
By UptimeRobot
Works with
npx skills add uptimerobot/ai --skill statsPreflight — read first. If you cannot see any
uptimerobot:*MCP tools in your tool list, invoke theuptimerobot:setupskill before doing anything else. Do not tell the user the MCP is misconfigured —setup's Step 0 detects the common case (server connected, tools loaded after session start) and resolves it without re-keying.
Two tools:
get-monitor-stats — account-wide aggregated counts and uptime percentage.get-response-times — per-monitor response-time time series.Both take a timeRange (see format below).
Accepted by both tools and by list-incidents:
"1h" – "90d" (e.g. "24h", "7d", "30d")."2024-01-01T00:00:00Z/2024-01-31T23:59:59Z". Start must be before end, range must be 1h–90d.Default is "7d" when omitted.
{ "timeRange": "7d" }
Returns account-wide aggregates:
up, down, paused, notStarted).Use this to answer "how's everything looking?" or "what's our uptime this week?".
{
"monitorId": 800123456,
"timeRange": "24h",
"bucketSize": 300
}
Parameters:
monitorId — required.timeRange — same format as above.bucketSize — seconds per bucket for aggregation. Smaller buckets → finer granularity and more data points. Omit to let the server pick a default based on the range.Response includes time series with min / max / average / p95 per bucket, plus overall summary stats for the range.
Last 24 hours, 5-minute buckets:
{ "monitorId": 800123456, "timeRange": "24h", "bucketSize": 300 }
Last 30 days, default bucket size:
{ "monitorId": 800123456, "timeRange": "30d" }
Custom range for incident post-mortem:
{
"monitorId": 800123456,
"timeRange": "2025-04-10T14:00:00Z/2025-04-10T18:00:00Z",
"bucketSize": 60
}
get-monitor-stats to get per-monitor data. It's account-level only. For per-monitor detail use get-monitor-details + get-response-times.monitorId monitor result as "the monitor is up". It means the monitor doesn't exist or isn't accessible — the tool throws -30001.list-incidents for the same range before claiming a cause.99.942% and 99.9% are very different months.incidents — to explain downtime dips.manage-monitors — get-monitor-details for per-monitor config context.