Has your website exposed tools for AI agents?
WebMCP is an experimental proposed web standard that allows websites to expose structured tools to supported browser agents. This checker looks for direct WebMCP implementation and supporting agent-readiness signals on a public webpage.
Source-level public-page check. No login or form submission is performed.
What this checker looks for
Declarative tools. WebMCP lets a site make an existing HTML form agent-callable with toolname and tooldescription attributes. A form counts as a registered declarative tool only when both required attributes are present and non-empty. We scan the fetched page markup for them.
Imperative tools. Sites can also register tools in JavaScript through navigator.modelContext.registerTool(). We statically inspect inline scripts and a disclosed sample of same-origin script files. Tools may be registered dynamically, lazy-loaded, available after authentication, or otherwise missed by static source inspection, so an absence here is not conclusive.
Origin-trial token. WebMCP is an experimental proposed web standard currently available through a Chrome origin trial. We check the response headers and meta tags for a token. A missing token means the origin trial is not enabled for this response; it is not proof that no WebMCP source code exists.
Supporting foundations. Separately from WebMCP, we report signals that may help agents and other machines work with a page: an llms.txt summary file, HTML accessibility signals, semantic landmarks, Schema.org structured data, and the page title and description. These are supporting signals, not WebMCP implementation, and none of them produces a score. WebMCP tool schemas use JSON Schema and are unrelated to Schema.org structured data.