‹ all guides

Sources checked 2026-11-03

Agentic Resource Discovery and resource catalogs

Resource catalogs describe the agent-facing interfaces a site exposes. This guide distinguishes ARD revisions, earlier AI Catalog conventions and the resources those manifests point to.

Agentic Resource Discovery, or ARD, is an open specification for telling AI agents what a site offers, in one machine-readable file. Instead of inferring from pages whether a site has an MCP server, an agent interface or an API, the site publishes a single index that names each resource and where to reach it. The specification appeared in 2026, is licensed under Apache 2.0, and builds on the AI Catalog data model, whose working group sits under the Linux Foundation, as its June 2026 announcement states.

What the manifest contains

A site advertises its agentic resources by serving a static JSON manifest under /.well-known. ARD v0.91, published 26 August 2026, names the file /.well-known/ard.json and the link relation ard, and says a conformant client MUST read that path. The predecessor path /.well-known/ai-catalog.json and the relation ai-catalog are ones a client MAY also consult. A site that serves only the old path may therefore not be found by a client that follows the current revision.

The current specification defines the manifest itself as a JSON document holding an entries array. Other top-level members, such as the specVersion and host fields the predecessor AI Catalog convention still carries, are transport-defined and ignored by ARD. Each entry describes one resource with a stable identifier, a display name, a type and a url or inline data.

An ARD entry SHOULD also carry representativeQueries, two to five sample questions the resource can answer. A registry builds its search index from them, so an entry without them cannot be found by search. The schema still accepts an entry without them and the conformance tester only warns, so a manifest can validate and still stay out of a registry's search results.

A resource can be an MCP server, an A2A agent, an API or a skill set. A registry can crawl published catalogs and answer a capability query by pointing an agent at the right resource.

Where it sits, and how it differs from llms.txt

ARD is a discovery layer, not a transport. It helps an agent find the right resource, which the agent then calls through that resource's own protocol, whether MCP, A2A or a plain API. Discovery comes first and invocation second. The catalog does not replace the manifests it points to. It indexes them, so a site keeps its server card, its agent card and its OpenAPI description, and adds one file that ties them together.

llms.txt tells an agent where a site's content lives. An ai-catalog or ard manifest tells an agent which agentic resources the site exposes and how to reach them. The two are complementary, and neither is a ranking file. Google has said publicly that llms.txt does not affect its search results, and the same holds for a resource catalog: neither changes ranking in Google Search. That is a statement about Google Search specifically.

An ARD registry is a different kind of index. It crawls published catalogs and answers a capability query over them through its own required search API. These files are therefore read by agents that act and by the registries that index them for that purpose. A general web search engine may still crawl and index such a file, and Google says that does not mean it treats the file in a special way.

Draft status and how to validate a manifest

The specification is early. As of October 2026 the repository carries a versioned draft, v0.91, whose own status line calls it a Proposal, and a normative change to the spec or its schemas starts as an issue before a maintainer lands it. Publishing a manifest today still means validating it against the draft revision the client you care about actually reads, rather than assuming one fixed shape.

What a scan checks, and why it matters now

A technical scan can check whether a manifest resolves at the declared path, parses as valid JSON and names entries with a url that answers. A manual review reads whether those entries point at resources that actually work, and whether the descriptions match what the resource does. Neither checks whether an agent has found the catalog through observed use, which is a separate question from whether the file exists and parses.

Adoption has started. A June 2026 check against public well-known paths found no discoverable ai-catalog.json at any of the launch partners the announcement shows. On 31 October 2026 two large hosts, github.com and huggingface.co, both served one at /.well-known/ai-catalog.json with the application/ai-catalog+json media type.

The value is the same as every other discovery surface. A capability an agent cannot find is a capability that does not exist for that agent, and one predictable file turns a set of separate manifests into a single answer.

turva.dev indexes the same four resources at both paths. The first is /.well-known/ard.json, with the MCP Server Card media type on its MCP entry and rel="ard" in every page head. The second is /.well-known/ai-catalog.json, for clients and scanners that still read the predecessor. Only ard.json carries representativeQueries for each entry. Both index its MCP server, its A2A agent, its API and its agent skills, each of which already resolves on its own.

The separate MCP Server Card discovery document, from the extension repository that is still labeled experimental, keeps its own convention, an AI Catalog at /.well-known/ai-catalog.json. The two profiles are therefore described apart and not merged. For an audit of a site's discovery surface, contact info@turva.dev.

Frequently asked

What is an ai-catalog.json?

An ai-catalog.json is a static JSON manifest at /.well-known/ai-catalog.json that lists the agentic resources a site offers, such as its MCP server, A2A agent and API. Each has an identifier, type, url and description. That lets agents and registries discover them from one file. Since ARD v0.91 the same manifest shape is published as /.well-known/ard.json, and ai-catalog.json is the predecessor path that a client may still consult.

Does Agentic Resource Discovery affect search ranking?

No. ARD is a discovery layer for AI agents, not a web search ranking file, though an ARD registry does crawl and index published catalogs so an agent can query them. Google has said publicly that llms.txt does not affect its Google Search results, and the same applies to a resource catalog's effect on Google Search ranking.

Where does an ai-catalog.json live?

Under ARD v0.91 at /.well-known/ard.json, announced with a link rel="ard" in the page head. The draft says a conformant client MUST read that path and MAY also consult the predecessor /.well-known/ai-catalog.json. Serve ard.json, and keep ai-catalog.json while clients and scanners still read it. Agents and registries read the resources a site offers from that path instead of inferring them from its pages.

Sources