The Agent Name Service (ANS), developed under the OWASP GenAI Security Project – Agentic Security Initiative, introduces a secure, DNS-inspired framework for AI agent discovery. ANS leverages Public Key Infrastructure (PKI) for identity verification, structured JSON schemas for communication, and a protocol adapter layer supporting A2A, MCP, and ACP protocols.
The architecture defines a comprehensive naming structure (ANSName) that encodes protocol, agent capability, provider, and version metadata, enabling consistent, secure resolution across diverse agent networks. Security measures include PKI-backed identity verification, digital signatures, and Zero-Knowledge Proofs (ZKP) for capability validation.
The MAESTRO 7 Layers framework is used to identify and mitigate threats such as agent impersonation, registry poisoning, and DoS attacks. ANS serves as a foundational layer for scalable, interoperable, and secure AI agent ecosystems, promoting trusted interactions across multi-agent platforms.
