Announcing the Agentic Resource Discovery specification

Summary

Agentic Resource Discovery (ARD) is an open specification for publishing, discovering, and verifying AI capabilities across the web, addressing the lack of a standard that works across organizations and ecosystems. It uses organization-hosted catalogs, including an ai-catalog.json file at a well-known domain path, plus federated registries that crawl, index, and return capabilities with trust metadata. Clients can query a registry with plain-language intent or fetch a known catalog directly, verify the publisher’s cryptographic identity, then connect at runtime through the capability’s native protocol or API. Google Cloud is bringing ARD to Gemini Enterprise Agent Platform through Agent Registry, which supports hosted discovery and governance features including namespaced URNs, egress policies, specification pinning, and Agent Identity trust-manifest verification. The specification is available under Apache 2.0, with native Agent Platform support planned in the coming months.

Takeaways

1. 1

   Providers can publish an ai-catalog.json file under their own domain, describing MCP servers, A2A agents, OpenAPI tools, or nested catalogs.

2. 2

   ARD discovery can use a plain-language registry query or bypass search with a direct fetch from a known partner domain.

3. 3

   Agent Registry in Gemini Enterprise Agent Platform provides governance features including namespaced URNs, agentic egress policies, specification pinning, and Agent Identity verification.