Agent Wranglers

Ready for AI agents Optional

Keep one catalogue of agent tools

List your MCP servers, agents and skills in /.well-known/ai-catalog.json. Link it from every page.

How to do it

Serve an AI Catalog as application/ai-catalog+json with specVersion and entries. Give each entry an identifier, a type (the media type of what it points to) and a url. Link it with rel="ai-catalog". The format is a working draft hosted by the Linux Foundation for the A2A and MCP projects.

Example

{
  "specVersion": "1.0",
  "host": { "displayName": "Example Co.", "identifier": "example.com" },
  "entries": [
    {
      "identifier": "urn:air:example.com:mcp:bookings",
      "displayName": "Example Co. bookings",
      "type": "application/mcp-server-card+json",
      "url": "https://example.com/mcp/server-card"
    },
    {
      "identifier": "urn:air:example.com:a2a:helper",
      "displayName": "Example Co. assistant",
      "type": "application/a2a-agent-card+json",
      "url": "https://example.com/.well-known/agent-card.json"
    }
  ]
}
<link rel="ai-catalog" href="/.well-known/ai-catalog.json">

How to check

The catalog parses as JSON. Every entry's URL answers 200 with the media type named in its type.

For agents: if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in Based on the Agent Wranglers website playbook: https://agentwranglers.se/playbook/website/ready-for-ai-agents/agentic-resource-discovery.