对比五种AI代理注册方案，揭示中心化、企业与分布式架构的权衡。
Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approaches
- 提出五种注册方案：从中心化到去中心化，涵盖JSON描述、IPFS路由、SaaS目录等
- 在安全、认证、扩展性、可维护性四维度评估，发现各方案各有优劣
- 适合关注AI代理互操作性与身份可信的开发者与架构师参考
自主AI代理如今在云、企业及去中心化领域运行，推动对可信赖发现、能力协商和身份保障的注册基础设施需求。我们分析了五种代表性方案：(1) MCP Registry（集中式发布mcp.json描述文件），(2) A2A Agent Cards（去中心化自描述JSON能力声明），(3) AGNTCY Agent Directory Service（基于IPFS Kademlia DHT的内容路由，支持语义分类发现、OCI artifact存储及Sigstore验证完整性），(4) Microsoft Entra Agent ID（集成策略与零信任的企业SaaS目录），(5) NANDA Index AgentFacts（可密码学验证、隐私保护的事实模型，含凭证断言）。通过安全、认证、可扩展性与可维护性四个维度评估，揭示中心控制、企业治理与分布式韧性之间的架构权衡。最后提出面向新兴人工智能代理互联网的设计建议：需具备可验证身份、自适应发现流程与可互操作的能力语义。
原文摘要 · Abstract (English)
Autonomous AI agents now operate across cloud, enterprise, and decentralized domains, creating demand for registry infrastructures that enable trustworthy discovery, capability negotiation, and identity assurance. We analyze five prominent approaches: (1) MCP Registry (centralized publication of mcp.json descriptors), (2) A2A Agent Cards (decentralized self-describing JSON capability manifests), (3) AGNTCY Agent Directory Service (IPFS Kademlia DHT content routing extended for semantic taxonomy-based content discovery, OCI artifact storage, and Sigstore-backed integrity), (4) Microsoft Entra Agent ID (enterprise SaaS directory with policy and zero-trust integration), and (5) NANDA Index AgentFacts (cryptographically verifiable, privacy-preserving fact model with credentialed assertions). Using four evaluation dimensions: security, authentication, scalability, and maintainability, we surface architectural trade-offs between centralized control, enterprise governance, and distributed resilience. We conclude with design recommendations for an emerging Internet of AI Agents requiring verifiable identity, adaptive discovery flows, and interoperable capability semantics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。