Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Some successful checks reached the service and some stopped at an authentication response; figures combine both.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 36 min ago | mcp initialize | ok | 200 | 514 ms | server ai-rete-rag · protocol 2025-06-18 · 9 tools |
| 36 min ago | mcp initialize | ok | 401 | 460 ms | auth required |
| 2 h ago | mcp initialize | ok | 200 | 467 ms | server ai-rete-rag · protocol 2025-06-18 · 9 tools |
| 2 h ago | mcp initialize | ok | 401 | 481 ms | auth required |
| 3 h ago | mcp initialize | ok | 200 | 529 ms | server ai-rete-rag · protocol 2025-06-18 · 9 tools |
| 3 h ago | mcp initialize | ok | 401 | 504 ms | auth required |
| 4 h ago | mcp initialize | ok | 200 | 522 ms | server ai-rete-rag · protocol 2025-06-18 · 9 tools |
| 4 h ago | mcp initialize | ok | 401 | 465 ms | auth required |
| 5 h ago | mcp initialize | ok | 200 | 562 ms | server ai-rete-rag · protocol 2025-06-18 · 9 tools |
| 5 h ago | mcp initialize | ok | 401 | 516 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.
Connect AI agents to Exa for web search, content fetching, and multi-step research.