What is AgentFacts?

1 min read Updated

A portable, verifiable credential standard (from the NANDA protocol) that AI agents carry across platforms to prove their identity, authority, and compliance status — analogous to a digital passport for agents.

WHY IT MATTERS

Before an agent can be governed, it needs to be identified. AgentFacts provides a standardised way for agents to prove who they are, who authorised them, and what compliance requirements they meet.

This is the identity layer that policy enforcement depends on. Without verified identity, per-agent scoping and audit attribution are impossible.

AgentFacts isn't theory — define it as policy in PolicyLayer and it's enforced on every tool call.

ENFORCE THIS WITH POLICY →

Enforced before the call runs. Nothing to install.

HOW POLICYLAYER USES THIS

PolicyLayer's per-agent scoping can leverage AgentFacts credentials to map agent identities to policy sets — verified identity drives verified enforcement.

FURTHER READING

// THE REGISTRY

Every MCP server your agents touch has a registry record.

Type a name, get the breakdown: verified identity, auth posture, risk grade, every tool classified, recommended policy. Re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

Take your agents live. Without losing control.

Route your MCP traffic through PolicyLayer. Every tool call is checked against your policy before it runs: allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

Instant setup, no code required.

46,500+ MCP servers and 515,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.