Agentic Resource Discovery (ARD)

Agentic Resource Discovery (ARD) is a proposed open standard for the discovery layer that sits in front of every agentic protocol — the step before invocation, where a client asks "what is available for this task?" and gets back a ranked set of MCP servers, agent cards, skills, workflows and APIs it could use. Publishers describe their resources once in an AI Catalog manifest at /.well-known/ai-catalog.json on their own domain, anchored by a urn:air: URN derived from that domain; independent discovery services crawl those manifests and expose them through a small REST interface whose only mandatory endpoint is POST /search. It deliberately does not execute anything — MCP, A2A and OpenAPI keep that job — and it deliberately does not try to be the one registry, inverting the submit-to-a-registry model in favour of publish-to-your-own-domain. Published as a v0.9 draft proposal on 28 May 2026 under Apache 2.0 by three authors at Microsoft, Google and Hugging Face, with a contributors wall of eleven organizations. It has no foundation, no charter, no participant roster and no working groups; it does have nine public architecture decision records and an official conformance CLI. This repo profiles it as a coalition with artifacts, and measures the distance between the specification and the endpoint.

Kin Score

This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.

How we profile Agentic Resource Discovery (ARD)

Each block below is one kind of artifact we hold for Agentic Resource Discovery (ARD). For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.

APIs 2

Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.

Individual APIs this provider publishes, each with its own machine-readable definition.

ARD Registry API

The discovery interface a conformant Agent Registry exposes. POST /search is the only mandatory endpoint and takes a natural-language `text` query plus optional structured `filt...

AI Catalog Manifest

The publishing half of the standard — the JSON manifest a domain serves at /.well-known/ai-catalog.json declaring who the host is and what agentic resources it offers, each entr...

JSON Schema 1

Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.

Standalone JSON Schema definitions for this provider's data models.

AICatalogManifest

3 properties

JSON SCHEMA

Resources

Every other property we hold for Agentic Resource Discovery (ARD) — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.

← All providers · Data indexed from github.com/api-evangelist/agentic-resource-discovery · machine-readable index on apis.io