aarnphm.xyz publishes an Agentic Resource Discovery manifest at
/.well-known/ai-catalog.json, declaring what an AI agent can call on this domain.
Everything below is read from that file. First seen by our crawler on 31 August 2026.
| Declared resource | Type |
|---|---|
| aarnphm.xyz Garden MCP Serverauth required OAuth-protected MCP server for searching and retrieving public notes from aarnphm's garden. endpoint: https://aarnphm.xyz/.well-known/mcp/server-card.jsonidentifier: urn:air:aarnphm.xyz:server:garden-mcppublished to be found for: search aarnphm's garden for notes about mechanistic interpretability · retrieve the full text of a public garden note · find aarnphm's writing about compiler construction | application/mcp-server-card+json |
| aarnphm.xyz Agent Skills Catalognot yet checked Discovery index for Garden skills covering content, flashcards, compiler construction, Quartz plugins, and interactive diagrams. endpoint: https://aarnphm.xyz/.well-known/agent-skills/index.jsonidentifier: urn:air:aarnphm.xyz:catalog:agent-skillspublished to be found for: create flashcards from a garden note · add descriptions to garden content files · build an interactive diagram for a technical note | application/json |
| aarnphm.xyz MCP OpenAPI Descriptionnot yet checked OpenAPI description of the garden MCP Streamable HTTP, OAuth, and health endpoints. endpoint: https://aarnphm.xyz/openapi.jsonidentifier: urn:air:aarnphm.xyz:schema:garden-openapipublished to be found for: show me how to call aarnphm.xyz's MCP endpoint · what OAuth flow and scope does the garden MCP server require · show the request and response schemas for the garden MCP API | application/json |
https://aarnphm.xyz/.well-known/ai-catalog.json, this publisher's own file.
Identifiers are reproduced exactly as published.
Note: this is the pre-v0.91 path. The specification renamed the manifest to /.well-known/ard.json, and most of the ecosystem still serves the older name.
None of these endpoints has been probed for reachability yet, so nothing here says whether they answer.
"Answers" and "no response" describe only whether an endpoint replied when last probed:
services go down and come back, and an entry is demoted rather than removed. None of this
is a trust, quality or safety rating.
https://neuronto.com/search, or connect an agent to https://neuronto.com/mcp.
If this is your domain, the free console shows what a registry
sees when it reads your manifest.