One spend ceiling per agent job, as MCP tools. Bound to a task_ref you pass, not a calendar month.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Every successful check was an authentication response (401/403). The endpoint exists and enforces authentication; nothing behind that boundary — tools, behaviour, service health — has been observed. Latency here is time to authentication response. Tools: not measured — authentication required.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 41 min ago | mcp initialize | ok | 401 | 330 ms | auth required |
| 2 h ago | mcp initialize | ok | 401 | 180 ms | auth required |
| 3 h ago | mcp initialize | ok | 401 | 171 ms | auth required |
| 4 h ago | mcp initialize | ok | 401 | 173 ms | auth required |
| 5 h ago | mcp initialize | ok | 401 | 170 ms | auth required |
| 6 h ago | mcp initialize | ok | 401 | 179 ms | auth required |
| 7 h ago | mcp initialize | ok | 401 | 334 ms | auth required |
| 8 h ago | mcp initialize | ok | 401 | 327 ms | auth required |
| 9 h ago | mcp initialize | ok | 401 | 334 ms | auth required |
| 10 h ago | mcp initialize | ok | 401 | 368 ms | auth required |
Attributed to the source that supplied each field. Treated as claims, not facts.
No long description beyond the summary.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.