Checks npm packages, lockfiles, agent skills and MCP servers for malware before you install them. Free lockfile check and known-bad lookup; full behavioral scans with file-and-line evidence.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 15 min ago | mcp initialize | ok | 200 | 133 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 1 h ago | mcp initialize | ok | 200 | 124 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 2 h ago | mcp initialize | ok | 200 | 144 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 3 h ago | mcp initialize | ok | 200 | 123 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 4 h ago | mcp initialize | ok | 200 | 127 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 5 h ago | mcp initialize | ok | 200 | 126 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 6 h ago | mcp initialize | ok | 200 | 125 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 7 h ago | mcp initialize | ok | 200 | 251 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 8 h ago | mcp initialize | ok | 200 | 160 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
| 9 h ago | mcp initialize | ok | 200 | 252 ms | server lazaretto 1.0.0 · protocol 2025-06-18 · 10 tools |
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.