E-commerce: how ready are these sites for AI agents?
Storefronts that sell products. Agents read e-commerce pages to identify items, compare prices, check availability, and surface them in shopping flows.
Share of measured e-commerce sites failing each check. The denominator is sites where the check actually ran — a check we skipped is never counted as a pass.
robots.txt advertises Content-Signal directives (e.g. `Content-Signal: ai-train=no, ai-summarize=yes`) that let agents respect granular usage preferences.
An MCP Server Card is reachable at `/.well-known/mcp/server-card.json` (or referenced from a Link header) and validates against the Model Context Protocol spec.
An API catalog is published at `/.well-known/api-catalog` (RFC 9727) or an OpenAPI document is reachable at `/openapi.json` or `/openapi.yaml`.
The site signals support for the Web Bot Auth IETF draft (HTTP Message Signatures over a known JWKS) so well-behaved agents can prove identity.
No published agent skills, so an agent has no described path to purchase.
No MCP endpoint, so an agent cannot transact programmatically.
`/.well-known/oauth-authorization-server` is reachable and conforms to RFC 8414, letting agents discover authorization endpoints without out-of-band setup.
No sitemap, so an agent has to guess which pages are products.
`/.well-known/oauth-protected-resource` is published per RFC 9728 so agents can discover required scopes and authorization servers programmatically.
Requests with `Accept: text/markdown` return a markdown representation of the page (Markdown content negotiation).
Same rubric, same checks, told as three gates: can an agent find your products, read your prices, and reach your checkout. Free, about 30 seconds.
Check my store, free →Every figure here is a real measurement against our published rubric, recomputed as we re-scan. Sites that disallow AgentSpeedBot in robots.txt are excluded before we fetch them.