Enables agents to vet MCP servers and agent configurations before trusting them, using local static analysis to detect injection, dangerous capabilities, exfiltration paths, and CVEs, with policy-based gating for CI.
Enables MCP-capable agents to perform independent security scanning, remediation, and fix verification, producing offline-re-derivable Verified Fix Records from the project's own checks.
Enables local spend caps and Ed25519-signed provenance receipts for AI agent tool calls, allowing any MCP host to gate model usage and independently verify signed decisions without sending prompts or content.