Security gateway for MCP agents: blocks prompt-injection-driven tool calls (poisoned payments, fabricated results) with cryptographic receipts, value-provenance enforcement, and multi-model consensus. The verification layer no syntactic MCP firewall has.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
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.