publica.la agentic web readiness

A+ Manifest validity: 89% (8/9 valid, 2 errors, 11 warnings) · Surface score 75 (coverage 50 + breadth 15 + conformance 10). 10 standards observed across 5 of 9 steps; 9 manifests present, 2 errors, 11 warnings. Checked 2026-10-23 15:00:53 UTC. This grades the agent-facing files published at publica.la, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/publica.la.svg) · JSON · Markdown · Re-check now

Coverage by step

Manifests

What an agent can call

• MCP endpoint https://docs.publica.la/mcp (streamable-http) — from /.well-known/ard.json
• MCP endpoint https://docs.publica.la/mcp (streamable-http) — from /.well-known/ai-catalog.json
• MCP endpoint https://publica.la/mcp (streamable-http) — from /.well-known/mcp.json
• MCP endpoint https://publica.la/mcp (streamable-http), tools: search_site_content, get_blog_post, list_changelog_entries, get_pricing_plans, get_platform_overview — from /.well-known/mcp/server-card.json
• A2A agent publica.la at https://publica.la/api/a2a, skills: publica.la site guide
• A2A agent publica.la at https://publica.la/api/a2a, skills: publica.la site guide
• API description https://publica.la/openapi.json (application/json)
• API description https://publica.la/openapi.json (application/json)
• API description https://publica.la/openapi.json (application/json)
• API description https://publica.la/en/developers (text/html)
• API description https://publica.la/llms.txt (text/plain)
• API description https://docs.publica.la/rest-api-v3/content/content-v3-overview (text/html)
• API description https://docs.publica.la/rest-api-v3/content/content-v3-sandbox (text/html)
• API description https://publica.la/.well-known/mcp/server-card.json (application/json)
• API description https://publica.la/en/developers#mcp (text/html)
• API description https://publica.la/.well-known/mcp.json (application/json)
• API description https://publica.la/.well-known/agent-card.json (application/json)
• API description https://publica.la/en/developers#agents (text/html)
• API description https://publica.la/agents.md (text/markdown)
• llms.txt: publica.la, 73 links, llms-full.txt present
• robots.txt AI policy: blocks CCBot, Bytespider; unlisted crawlers partial
• OAuth protected resource https://publica.la, authorization servers:

Standards observed

• Agent2Agent Protocol https://publica.la/.well-known/agent-card.json
• llms.txt https://publica.la/llms.txt
• Content Signals Policy https://publica.la/robots.txt
• Agentic Resource Discovery https://publica.la/.well-known/ard.json
• AI Catalog well-known file https://publica.la/.well-known/ai-catalog.json
• api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://publica.la/.well-known/api-catalog
• auth.md https://publica.la/auth.md
• AI Crawler User-Agent Tokens in robots.txt https://publica.la/robots.txt
• OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization) https://publica.la/.well-known/oauth-protected-resource
• Agent Skills https://publica.la/.well-known/agent-skills/index.json

Cheapest next steps

1. AGENTS.md: instructions for coding agents working on or with the site
2. security.txt (RFC 9116): RFC 9116 contact and expiry, read by agents and people

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback openapi). Call the MCP endpoint at https://docs.publica.la/mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://docs.publica.la/mcp POST a JSON-RPC tools/list, or server/discover on the 2026-07-28 revision, before reading HTML.

Practical readability: exa_parsable yes, markdown negotiation no, render ssr_rich, HTML quality high, first content at byte 52815, JSON-LD Organization, ImageObject, PostalAddress, ContactPoint, OfferCatalog, Offer, Service, UnitPriceSpecification, WebSite, VideoObject, SoftwareApplication, Review, Person.

AI crawler posture: search_partially_blocked · Assistant access: OpenAI partial, Anthropic partial, Google partial, Perplexity partial, Exa partial.

Readiness subscores: reach 18/20, readability 22/30, capabilities 35/35, conformance 10/15, total 85/100, grade A+.

How the grade is made

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). Lifecycle grade: A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Strict 100-point composite (subscores.total_100 / subscores.grade_100): reach_and_policy (20) + readability (30) + capabilities (35) + conformance (15), where A+ >= 80, A >= 65, B >= 45, C >= 28, D >= 15. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules