Add: Universal Trust Adapter — credential verification infrastructure for AI agent security

[alicelabsllc]

What

Universal Trust Adapter (UTA) — credential verification infrastructure for AI agent security.

• Repo: https://github.com/alicelabs-llc/universal-trust-adapter
• API: https://www.marketnow.site/api/trust

What it does

UTA provides a universal credential verification layer for AI agents. Before an agent invokes a tool, UTA verifies the tool's credential through a 12-stage pipeline.

8 formats: ATC v3, JWT, W3C VC, A2A, EAT-AI, ZTA, MCP Server Cards, X.509

12 stages: PARSER → DETECT → SCHEMA → CRYPTO → ISSUER → KEY_BINDING → POP → PROVENANCE → LIFECYCLE → EVIDENCE → POLICY → DECISION

Golden rule: UNKNOWN = DENY. Fail-closed by design.

Why it matters for agent security

Agents are moving from demos to production. In production:

• An agent that invokes a tool with a revoked credential creates a security incident
• An agent that trusts any MCP server is open to supply chain attacks
• An agent that can't verify credentials can't make trust decisions

UTA gives agents the ability to verify, then decide.

Stats

• 6,744 verifications/sec
• 480+ tests
• 23 conformance vectors (public, reproducible)
• Free API, no auth, CORS open
• NPM: @marketnow/trust-core

Suggested entry

- [Universal Trust Adapter (UTA)](https://github.com/alicelabs-llc/universal-trust-adapter) - Credential verification for AI agents. 12-stage pipeline, 8 formats, fail-closed. Free API.