Back to Glossary
PROTO

Per-Action Verification Model

never trust always verifyagentic security posturecontinuous verification

The per-action verification model treats each routed tool call as an independent authorization event, rejecting the assumption that trust persists across actions.

WHY SESSION TRUST IS INSUFFICIENT

Traditional session-based security assumes a principal remains legitimate. AI agents invalidate this: a Prompt Injection attack mid-session can redirect an agent toward unauthorized actions. Per-action verification is required.

PROTOCOL CONTEXT (VEX PROTOCOL / MCPVANGUARD)

McpVanguard supports per-routed-call verification, while VEX is designed to support transition-level verification. In McpVanguard's hosted (SSE/HTTP) mode, routed calls can carry authorization context; local stdio mode provides deterministic enforcement without authentication.

ProvnAI Mitigation

McpVanguard independently evaluates routed tool calls against the active rule set, reducing reliance on persistent session trust and supporting review of session-hijack signals.