Skip to content
Methodology

AI Catalog

ia.ai-catalog · 4.21

Find MAY Recommendation AR-FIND-04

Why it matters

An AI Catalog gives agents one machine-readable list of the AI resources of a site: MCP servers, APIs, skills and docs. Agents find it through links, so link it from the home page.

How to fix it

Publish /.well-known/ai-catalog.json and link it from the home page.

  1. Create /.well-known/ai-catalog.json with an entry for each MCP server, API, skill index and docs root.

    {
  "name": "Example",
  "resources": [
    {"type": "mcp", "url": "https://example.com/mcp"},
    {"type": "openapi", "url": "https://example.com/openapi.json"}
  ]
}

  2. Serve the file as application/json with HTTP 200.

  3. Link the catalog from the home page or from llms.txt.

Verify

curl -sf https://{domain}/.well-known/ai-catalog.json | jq -e 'type == "object"'

Expected: exit code 0

Run a new scan for this checkpoint:

isagentready results {domain} --checkpoint ia.ai-catalog
Details Mapping, lifecycle and references
AR mapping
Full match
Score role
Bonus
Introduced
2026-08-24
Methodology version
2026-10-22

Checkpoint data (JSON)