What does the agent readiness check test?

Real protocol probes of .well-known files (openapi.json, mcp.json, ai-plugin.json, security.txt), a live MCP initialize handshake, A2A agent-card validation, a 20-user-agent crawler audit, and a JS-parity check.

Is warbyparker.com ready for AI agents?

AI agent readiness report · platform: Custom · checked 2026-10-20 · log in to re-run

22%

Readiness

2/9

Verified

Custom

Platform

Not agent-ready

Mcp

Webmcp

A2a

Anp

Ucp

Ap2

Openapi

Llms Txt

Wikidata

0/18 AI crawlers reached the homepage18 blocked

Ranks above 34% of 127 sites checkedcorpus avg 24/100

Not agent-ready

warbyparker.com has 2 of 9 readable agent standards in place; missing Mcp, Webmcp, A2a, Anp, Ucp, Ap2, Openapi.

Assessment

2 of 9 readable agent-readiness checks verified. 16 AI crawler user-agent(s) got an error at the edge although robots.txt allows them. See per-protocol drawers for evidence and fix-it files.

Per-protocol verdicts

Mcpno /.well-known/mcp.json, /mcp, or /.well-known/mcpNot found

Webmcpno navigator.modelContext.register, <script type="webmcp">, or <link rel="modelcontext"> in HTMLNot found

A2ano /.well-known/agent.json or /.well-known/agent-card.jsonNot found

Anpno /.well-known/did.jsonNot found

Ucpno /.well-known/ucpNot found

Ap2no /.well-known/ap2.jsonNot found

Openapino /openapi.json, /api/openapi.json, or /.well-known/openapi.jsonNot found

Llms Txt/llms.txt present, 1 sectionsVerified

WikidataWikidata entity Q7968882 (Warby Parker)Verified

.well-known files

.well-known/mcp.json164575 bytes200

Mcp Well Known Alt164368 bytes200

/mcp endpointnot found404

Ai Plugin Legacy164480 bytes200

.well-known/agent.json164593 bytes200

.well-known/agent-card.json164479 bytes200

Anp Did164579 bytes200

Openapi Well Known164578 bytes200

Openapi Root164506 bytes200

Openapi Api164463 bytes200

Ucp Profile164530 bytes200

Ap2 Well Known164456 bytes200

Llms Txt1746 bytes200

Llms Full Txt4943 bytes200

robots.txt1133 bytes200

sitemap.xml525 bytes200

AI crawler audit

0 of 18 AI user-agents reached the homepage; 16 returned an error to a request carrying their user-agent string although robots.txt allows it.

9 of 18 were tested with the operator's published user-agent string and the rest with the bare token, since no published string was found. A request that only names a user-agent does not prove the real crawler would be treated the same.

GPTBotHTTP 403Blocked

OAI-SearchBotHTTP 403Blocked

ChatGPT-UserHTTP 403Blocked

anthropic-aiHTTP 403Blocked

ClaudeBotHTTP 403Blocked

Claude-UserHTTP 403Blocked

Claude-SearchBotHTTP 403Blocked

PerplexityBotHTTP 403Blocked

What this means for warbyparker.com

On warbyparker.com (Custom), 2 of 9 readable agent standards are in place: Llms Txt, Wikidata. Missing: Mcp, Webmcp, A2a, Anp, Ucp, Ap2, Openapi.

Without JavaScript, your brand name still appears in the raw HTML, so crawlers that do not run JS can read it.

warbyparker.com scores higher than 34% of the 127 sites checked here so far; the average readiness score is 24/100.

Make warbyparker.com agent-ready

Start with the highest-impact gap: Mcp. Publish a working MCP endpoint at /.well-known/mcp.json (the initialize handshake must succeed, not just return 200), add an A2A agent card, and keep the crawler path clean.

Frequently asked questions

Are these real probes or AI guesses?

Real probes. We fetch the actual files, run a real MCP initialize handshake, and validate A2A cards against their schema. No model decides a verdict.

Does warbyparker.com need every standard to pass?

No. Start with the highest-impact gap above, then add the rest. Most sites win the most by shipping a working MCP endpoint and keeping the crawler path clean.

Check your own site free

Run the same protocol probes on any URL, then sign up free for the copy-paste fix-it files and the full 20-crawler audit.

Run a free check

Agent readiness on Custom

We have checked 64 other sites on Custom. The Custom hub aggregates protocol verification rates and average readiness scores across every Custom site checked here.

Is Custom ready for AI agents?