clerk.com agentic web readiness

A+ Manifest validity: 83% (5/6 valid, 2 errors, 6 warnings) · Surface score 65 (coverage 40 + breadth 15 + conformance 10). 10 standards observed across 4 of 9 steps; 6 manifests present (+ robots.txt, security.txt), 2 errors, 6 warnings. Checked 2026-10-25 13:54:31 UTC. This grades the agent-facing files published at clerk.com, not the organisation's products.

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

Coverage by step

Manifests

{
  "linkset": [
    {
      "anchor": "https://clerk.com/",
      "service-desc": [
        {
          "href": "https://clerk.com/openapi.json",
          "type": "application/openapi+json"
        }
      ],
      "service-doc": [
        {
          "href": "https://clerk.com/docs/api",
          "type": "text/html"
        }
      ],
      "service-meta": [
        {
          "href": "https://clerk.com/AGENTS.md",
          "type": "text/markdown"
        }
      ]
    }
  ]
}

What an agent can call

• MCP endpoint https://mcp.clerk.com/mcp (streamable-http) — from /.well-known/ai-catalog.json#urn:air:clerk.com:mcp:mcp-server
• MCP endpoint https://mcp.clerk.com/mcp (streamable-http) — from /.well-known/mcp/server-card.json
• API description https://clerk.com/docs/reference/spec/bapi/latest.yml (application/yaml)
• API description https://clerk.com/docs/reference/backend-api (service-doc)
• API description https://clerk.com/docs/reference/spec/platform/latest.yml (application/yaml)
• API description https://clerk.com/docs/reference/platform-api (service-doc)
• API description https://clerk.com/docs/reference/spec/fapi/latest.yml (application/yaml)
• API description https://clerk.com/docs/reference/frontend-api (service-doc)
• llms.txt: Clerk, 54 links, llms-full.txt present
• robots.txt AI policy: no AI crawler tokens named; unlisted crawlers allowed on public paths (subpaths disallowed under User-agent: *)
• OAuth protected resource https://clerk.com, authorization servers:
• ARD bridge (/.well-known/ai-catalog.json): 1/1 valid, 0 legacy, 0 dead/broken (served at deprecated path only)

Standards observed

• llms.txt https://clerk.com/llms.txt
• Content Signals Policy https://clerk.com/robots.txt
• AI Catalog well-known file https://clerk.com/.well-known/ai-catalog.json
• api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://clerk.com/.well-known/api-catalog
• auth.md https://clerk.com/auth.md
• OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization) https://clerk.com/.well-known/oauth-protected-resource
• Agent Skills https://clerk.com/.well-known/agent-skills/index.json
• Markdown for Agents https://clerk.com/
• MCP Server Cards (SEP-2127)
• Model Context Protocol

Cheapest next steps

1. Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch (emerging spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "ard", "domain": "clerk.com"}))
2. AGENTS.md: instructions for coding agents working on or with the site
   Generate starter /AGENTS.md for clerk.com

   # Clerk for agents
   
   Clerk and what it offers to agents
   
   ## Read the data, not the HTML
   - Index: https://clerk.com/llms.txt
   - API description: https://clerk.com/openapi.json
   - Discovery catalog: https://clerk.com/.well-known/ard.json
   
   ## Calling
   - MCP server (Streamable HTTP): https://clerk.com/mcp
   - Rate limits and authentication: describe them here
   
   ## Conventions
   - How to cite or attribute content
   - What not to do (no scraping of /account/, no automated sign-ups, etc.)
   
   Contact: security@clerk.com
   

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback agent_skills). Call the MCP endpoint at https://mcp.clerk.com/mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://mcp.clerk.com/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 yes, render markdown_native, HTML quality high, first content at byte 0.

AI crawler posture: open_to_all · Assistant access: OpenAI allowed, Anthropic allowed, Google allowed, Perplexity allowed, Exa allowed.

Readiness subscores: reach 20/20, readability 30/30, capabilities 28/35, conformance 10/15, total 88/100, 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