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.

Agentic Resource Discovery (ARD) publishes 3 APIs on the APIs.io network: Agents API, Explore API, and Search API. Tagged areas include Agentic Resource Discovery, ARD, AI Catalog, Agent Discovery, and Discovery.

Agentic Resource Discovery (ARD)’s developer surface includes FAQ, getting-started guide, and 26 more developer resources.

🌐 Visit website 📡 Source on GitHub

25.7/100 emerging ▬ flat Agent 13/100 agent aware Full breakdown ↓
scored 2026-09-14 · rubric v0.22.0

1 APIs

Agentic Resource DiscoveryARDAI CatalogAgent Discovery DiscoveryWell-Known URIMedia Types Federation MCP A2A Agent Skills Standards Standards Body SpecificationMachine Readability

Kin Score

Kin Score How this is scored →
scored 2026-09-14 · rubric v0.22.0

Composite quality — 25.7/100 · emerging

Contract Quality 11.2 / 23

Developer Ergonomics 3.9 / 18

Access Clarity 0.0 / 18

Operational Transparency 3.4 / 12

Contract Governance 0.0 / 11

Discoverability 5.3 / 9

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 13/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 0 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/agentic-resource-discovery: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 4

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

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...

Agentic Resource Discovery (ARD) Agents API

The Agents API from Agentic Resource Discovery (ARD) — 1 operation(s) for agents.

Agentic Resource Discovery (ARD) Explore API

The Explore API from Agentic Resource Discovery (ARD) — 1 operation(s) for explore.

Agentic Resource Discovery (ARD) Search API

The Search API from Agentic Resource Discovery (ARD) — 1 operation(s) for search.

JSON Schema 1

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

AICatalogManifest

3 properties

JSON SCHEMA

Resources

Get Started 1

Portal, sign-up, and the first successful call

GettingStarted

GettingStarted

Documentation 3

Reference material describing how the API behaves

ContributionGuide

ContributionGuide

Specification

Specification

ReferenceImplementation

ReferenceImplementation

Design & Contract 1

Pagination, idempotency, versioning, errors, and events

Conformance

Conformance

Build 3

SDKs, sample code, and the tooling you integrate with

CodeOfConduct

CodeOfConduct

SourceCode

SourceCode

GitHubOrganization

GitHubOrganization

Access & Security 1

Authentication, authorization, and security posture

SecurityPolicy

SecurityPolicy

Operate 3

Status, limits, changes, and where to get help

IssueTracker

IssueTracker

Releases

Releases

FAQ

FAQ

Commercial 1

Pricing, plans, and the legal terms of use

License

License

Company 1

The organization behind the API

Website

Website

Other 14

Properties that don't map to a standard resource type

Contributing

Participants

Governance

TestSuite

Adopters

Adoption

People

Companies

Leads

Repositories

Contributors

WorkingGroups

Taxonomy

Glossary

Scroll for all 14

Source (apis.yml)

aid: agentic-resource-discovery
url: https://raw.githubusercontent.com/api-evangelist/agentic-resource-discovery/refs/heads/main/apis.yml
name: Agentic Resource Discovery (ARD)
deliveryModel:
  model: unknown
  open_source: unknown
  commercial: false
  callable_host: false
  label: Delivery model not determined — needs a product licence on record
  confidence: low
  source:
  - repository-unlicensed
  generated: '2026-08-28'
  method: derived
specificationVersion: '0.23'
kind: standard
x-type: standards-body
x-category: Specification
x-host: null
x-host-structure: null
created: 2026-05-19 00:00:00+00:00
modified: 2026-07-31
position: Producing
access: 3rd-Party
description: '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.'
tags:
- Agentic Resource Discovery
- ARD
- AI Catalog
- Agent Discovery
- Discovery
- Well-Known URI
- Media Types
- Federation
- MCP
- A2A
- Agent Skills
- Standards
- Standards Body
- Specification
- Machine Readability
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/agentic-resource-discovery.png
maintainers:
- FN: Kin Lane
  email: info@apievangelist.com
  X: apievangelist
  url: https://apievangelist.com
apis:
- aid: agentic-resource-discovery:ai-catalog-manifest
  name: AI Catalog Manifest
  description: '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 entry typed by media type, identified by a domain-anchored
    urn:air: URN, and carrying an optional trustManifest for identity, compliance attestations, provenance and a detached
    JWS signature. Defined upstream by the ai-catalog project and extended here with discovery attributes. This is the artifact
    an API provider actually has to write.'
  humanURL: https://agenticresourcediscovery.org/ai_catalog_spec/
  tags:
  - Discovery
  - Metadata
  - Well-Known URI
  properties:
  - type: JSONSchema
    url: json-schema/ai-catalog.schema.json
  - type: Specification
    url: https://agenticresourcediscovery.org/ai_catalog_spec/
  - type: Documentation
    url: https://agenticresourcediscovery.org/how_to_publish/
  - type: SourceCode
    url: https://github.com/Agent-Card/ai-catalog
- aid: agentic-resource-discovery:agentic-resource-discovery-agents-api
  name: Agentic Resource Discovery (ARD) Agents API
  description: The Agents API from Agentic Resource Discovery (ARD) — 1 operation(s) for agents.
  humanURL: https://agenticresourcediscovery.org/spec/
  tags:
  - Agents
  properties:
  - type: OpenAPI
    url: openapi/agentic-resource-discovery-agents-api-openapi.yml
  - type: Specification
    url: https://agenticresourcediscovery.org/spec/
  - type: Documentation
    url: https://agenticresourcediscovery.org/how_ard_works/
  - type: TestSuite
    url: conformance/README.md
- aid: agentic-resource-discovery:agentic-resource-discovery-explore-api
  name: Agentic Resource Discovery (ARD) Explore API
  description: The Explore API from Agentic Resource Discovery (ARD) — 1 operation(s) for explore.
  humanURL: https://agenticresourcediscovery.org/spec/
  tags:
  - Explore
  properties:
  - type: OpenAPI
    url: openapi/agentic-resource-discovery-explore-api-openapi.yml
  - type: Specification
    url: https://agenticresourcediscovery.org/spec/
  - type: Documentation
    url: https://agenticresourcediscovery.org/how_ard_works/
  - type: TestSuite
    url: conformance/README.md
- aid: agentic-resource-discovery:agentic-resource-discovery-search-api
  name: Agentic Resource Discovery (ARD) Search API
  description: The Search API from Agentic Resource Discovery (ARD) — 1 operation(s) for search.
  humanURL: https://agenticresourcediscovery.org/spec/
  tags:
  - Search
  properties:
  - type: OpenAPI
    url: openapi/agentic-resource-discovery-search-api-openapi.yml
  - type: Specification
    url: https://agenticresourcediscovery.org/spec/
  - type: Documentation
    url: https://agenticresourcediscovery.org/how_ard_works/
  - type: TestSuite
    url: conformance/README.md
common:
- type: IssueTracker
  url: https://github.com/Agent-Card/ai-catalog/issues
- type: SecurityPolicy
  url: https://github.com/Agent-Card/ai-catalog/blob/main/SECURITY.md
- type: CodeOfConduct
  url: https://github.com/Agent-Card/ai-catalog/blob/main/CODE_OF_CONDUCT.md
- type: ContributionGuide
  url: https://github.com/Agent-Card/ai-catalog/blob/main/CONTRIBUTING.md
- type: Website
  url: https://agenticresourcediscovery.org
- type: Specification
  url: https://agenticresourcediscovery.org/spec/
- type: SourceCode
  url: https://github.com/ards-project/ard-spec
- type: GitHubOrganization
  url: https://github.com/ards-project
- type: License
  url: https://github.com/ards-project/ard-spec/blob/main/LICENSE
- type: Contributing
  url: https://github.com/ards-project/ard-spec#contributing
- type: Participants
  url: https://agenticresourcediscovery.org/contributors/
- type: Governance
  url: governance/agentic-resource-discovery-governance.yml
- type: Conformance
  url: conformance/agentic-resource-discovery-conformance.yml
- type: TestSuite
  url: https://github.com/ards-project/ard-spec/tree/main/conformance
- type: ReferenceImplementation
  url: https://agenticresourcediscovery.org/ref_implementations/
- type: Adopters
  url: adoption/agentic-resource-discovery-adoption.yml
- type: Adoption
  url: adoption/agentic-resource-discovery-adoption.yml
- type: People
  url: people/agentic-resource-discovery-people.yml
- type: Companies
  url: companies/agentic-resource-discovery-companies.yml
- type: Leads
  url: leads/agentic-resource-discovery-new-company-leads.yml
- type: Repositories
  url: repositories/agentic-resource-discovery-repositories.yml
- type: Releases
  url: releases/agentic-resource-discovery-releases.yml
- type: Contributors
  url: contributors/agentic-resource-discovery-contributors.yml
- type: WorkingGroups
  url: working-groups/agentic-resource-discovery-working-groups.yml
- type: Taxonomy
  url: taxonomy/agentic-resource-discovery-taxonomy.yml
- type: Glossary
  url: https://agenticresourcediscovery.org/glossary/
- type: FAQ
  url: https://agenticresourcediscovery.org/faq/
- type: GettingStarted
  url: https://agenticresourcediscovery.org/get_started/

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/agentic-resource-discovery"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/agentic-resource-discovery/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/agentic-resource-discovery/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.