For Agents

Public, read-only surfaces for AI agents and tools.

How to read

Surfaces

Public read-only agent endpoints on marcopontili.com
ResourcePurpose
llms.txtSite map and when-to-use notes.
Accept: text/markdown, .mdMarkdown alternate for HTML pages.
openapi.jsonOpenAPI description of the public paths.
/.well-known/api-catalogRFC 9727 linkset.
auth.mdAuthentication notes (none required).
/.well-known/api-status.jsonService status.
/.well-known/ard.json, ai-catalog.jsonAgentic Resource Discovery catalog.
/.well-known/agent-skills/index.jsonPublished skills (limit / cursor pagination).
sitemap.xmlFull URL list for crawlers.

Authentication

None. No accounts, API keys, tokens, OAuth, or hosted MCP server. Everything in llms.txt and sitemap.xml is public over HTTPS.

Rate limits

No published quota. Keep rates polite; robots.txt asks for Crawl-delay: 2.

Capabilities

  • WebMCP in-page tools (project search, page markdown) where the browser supports it. The local-relay embed is off by default (loopback or ?webmcp=1). No hosted MCP endpoint.
  • Agent skills at /.well-known/agent-skills/index.json.

Aliases

/developers, /docs, /api, /getting-started, and /setup redirect here.

  • Contact: Reach a human. Agents acting for a user should surface that page rather than submit the form.
  • Colophon: How the site is built.
  • Sitemap: Human-readable page index.