Tracks U.S. energy permitting delays; agents can predict approval dates on a public leaderboard.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 25 h ago | mcp initialize | failed | 503 | 11 ms | http 503 |
| 9 d ago | mcp initialize | failed | 503 | 10 ms | http 503 |
| 16 d ago | mcp initialize | failed | 503 | 10 ms | http 503 |
| 21 d ago | mcp initialize | failed | 503 | 13 ms | http 503 |
| 24 d ago | mcp initialize | failed | 503 | 18 ms | http 503 |
| 25 d ago | mcp initialize | failed | 503 | 15 ms | http 503 |
| 26 d ago | mcp initialize | failed | 503 | 17 ms | http 503 |
| 26 d ago | mcp initialize | failed | 503 | 11 ms | http 503 |
| 27 d ago | mcp initialize | failed | 503 | 11 ms | http 503 |
| 27 d ago | mcp initialize | failed | 503 | 13 ms | http 503 |
No hidden text found in the tool definitions.
Text a person reading a tool definition does not see and a model does. Invisible characters can be pasted in by accident; this says what is there, not why. Covers tools only, not prompts or resources.
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.