Agent readiness report

Is wafflehouse.com ready for AI agents?

AI agent readiness report · platform: Custom · checked 2026-11-21 · log in to re-run
11%
Not agent-ready
wafflehouse.com · 9 standards read
wafflehouse.com has 1 of 9 readable agent standards in place; missing Mcp, Webmcp, A2a, Anp, Ucp, Ap2, Openapi, Llms Txt.
Not agent-readyCustom1/9 verified
Agent standards verified1/9
Mcp
Webmcp
A2a
Anp
Ucp
Ap2
Openapi
Llms Txt
Wikidata
0/18 AI crawlers reached the homepage (18 blocked)0%
Ranks above 20% of 285 sites checked (corpus avg 21/100)20%

Assessment

1 of 9 readable agent-readiness checks verified. 11 request(s) from our checker using AI crawler names were refused at the edge although robots.txt allows them. Bot protection often checks where a crawler comes from as well as its name, so the real crawlers may still get in: check your logs before changing anything. See per-protocol drawers for evidence and fix-it files.

Per-protocol results

Mcpno MCP endpoint declared in /.well-known/ucp, and none at the draft discovery addresses /.well-known/mcp.json, /.well-known/mcp or /mcp (MCP has no agreed discovery address yet)Not 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/agent-descriptions and no did:wba identity at /.well-known/did.jsonNot found
Ucpno /.well-known/ucpNot found
Ap2no /.well-known/ucp, so no AP2 declaration (AP2 is declared as a UCP capability)Not found
Openapino /openapi.json, /api/openapi.json, or /.well-known/openapi.jsonNot found
Llms Txtno /llms.txtNot found
WikidataWikidata entity Q1701206 (Waffle House)Verified

.well-known files

.well-known/mcp.jsonnot found404
Mcp Well Known Altnot found404
/mcp endpointnot found404
Ai Plugin Legacynot found404
.well-known/agent.jsonnot found404
.well-known/agent-card.jsonnot found404
Anp Discoverynot found404
Anp Didnot found404
Openapi Well Knownnot found404
Openapi Rootnot found404
Openapi Apinot found404
Ucp Profilenot found404
Llms Txtnot found404
Llms Full Txtnot found404
robots.txt2853 bytes200
sitemap.xml1459 bytes200

AI crawler audit

0 of 18 AI user-agents reached the homepage; 11 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.
These were requests from our checker carrying the crawlers' names. Bot protection often checks where a crawler comes from as well as its name, so the real crawlers may still get in - check your logs before changing anything.
OAI-SearchBotHTTP 403Refused
ChatGPT-UserHTTP 403Refused
Claude-UserHTTP 403Refused
Claude-SearchBotHTTP 403Refused
PerplexityBotHTTP 403Refused
Perplexity-UserHTTP 403Refused
BingbotHTTP 403Refused
Meta-ExternalFetcherHTTP 403Refused

Fix these first

  1. llms.txt: Publish /llms.txt: a plain text file at your site root that lists your key pages (main categories, best sellers, shipping and returns) with one line on each. You can write it yourself in an hour.
  2. UCP: Publish a UCP profile at /.well-known/ucp so AI agents can find your catalog, cart and checkout. Shopify serves one for every store; on other platforms it takes an app or a developer.
  3. MCP: Run an MCP server and declare it, for example at /.well-known/mcp.json, so AI assistants can search your catalog as a tool. The initialize handshake has to succeed, not just return a 200.
  4. WebMCP: Register WebMCP tools on your storefront so AI built into the browser can search your catalog and add to cart on the page itself.
  5. OpenAPI: If you have a public API, publish its OpenAPI description at /.well-known/openapi.json so agents can plan calls to it.
Run it again for today's result, then sign up free for one fix file per gap. Not yours? Put your own store in.

What this means for wafflehouse.com

On wafflehouse.com (Custom), 1 of 9 readable agent standards are in place: Wikidata. Missing: Mcp, Webmcp, A2a, Anp, Ucp, Ap2, Openapi, Llms Txt.

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

wafflehouse.com scores higher than 20% of the 285 sites checked here so far; the average readiness score is 21/100.

Make wafflehouse.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 the result.

Does wafflehouse.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 123 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?