Agent Name Service (ANS): A Universal Directory for Secure AI Agent Discovery and Interoperability

TL;DR

The paper presents the Agent Name Service (ANS), a DNS-inspired, protocol-agnostic registry for secure AI agent discovery that integrates PKI-based identity, JSON Schema-based communication, and a modular Protocol Adapter Layer. It defines a formal ANSName naming scheme, a secure resolution algorithm, and lifecycle management (registration, renewal, revocation) to support trustworthy, scalable agent ecosystems across diverse protocols (A2A, MCP, ACP). The architecture includes a configurable extension point for protocol adapters, threat modeling via MAESTRO, and a comprehensive set of security controls spanning PKI, registry integrity, and protocol integration. By providing a unified trust and discovery layer, ANS aims to enable interoperable agent marketplaces and secure autonomous interactions while balancing governance, scalability, and security concerns for real-world deployment.

Abstract

The proliferation of AI agents requires robust mechanisms for secure discovery. This paper introduces the Agent Name Service (ANS), a novel architecture based on DNS addressing the lack of a public agent discovery framework. ANS provides a protocol-agnostic registry infrastructure that leverages Public Key Infrastructure (PKI) certificates for verifiable agent identity and trust. The architecture features several key innovations: a formalized agent registration and renewal mechanism for lifecycle management; DNS-inspired naming conventions with capability-aware resolution; a modular Protocol Adapter Layer supporting diverse communication standards (A2A, MCP, ACP etc.); and precisely defined algorithms for secure resolution. We implement structured communication using JSON Schema and conduct a comprehensive threat analysis of our proposal. The result is a foundational directory service addressing the core challenges of secured discovery and interaction in multi-agent systems, paving the way for future interoperable, trustworthy, and scalable agent ecosystems.

Figures (6)

• Figure 1: ANS Architecture. Illustrates the interaction between Agent, ANS Service, Agent Registry, CA, RA, and Protocol Adapter Layer.
• Figure 2: Agent Registration Process.
• Figure 3: Agent Resolution Process.
• Figure 4: Full end-to-end flow (Registration, Resolution, Interaction).
• Figure 5: ANS Resolution Sequence as a Pre-Communication Step.