webmcpify.at Agent skill DOCS · REV 2026-08-31

OPEN SOURCE · MIT · VERSION 0.5.0 PREPARED

Docs for an inspectable WebMCP run.

webmcpify is a WebMCP agent skill for curated core coverage or route-by-route parity. These guides separate what the coding agent builds, what Chrome verifies, and what a client such as ChatGPT can actually see.

SOURCE-TRACEABLE, NOT A SCORECARD

Start with the surface you need

Coverage is a named choice

TargetEvidenceBest fit
curatedA reviewed route-to-tool map for selected high-value actions, with written omission reasons.A focused first integration and smaller active toolsets.
parityEvery interactive element on every authenticated route maps to a tool or a written reason.Auditable product-surface equivalence.

A raw tool count cannot prove parity. No public source or measured client run establishes a universal safe per-page tool count, so client-capacity gaps remain explicit instead of becoming a compatibility claim.

The three proof layers

  1. Manifest proof: the route map, policy fingerprint, approvals, examples and expected UI deltas are persisted in the target repository.
  2. Chrome proof: a dedicated headed profile enumerates and executes each tool against the recorded secure verification origin.
  3. Client proof: the exact client/account shows its supported subset of the page's registrations. In ChatGPT this surface is called Site tools; it currently discovers top-level imperative tools, not declarative forms or iframe registrations.

Current source boundary

Last reviewed 2026-08-31. WebMCP is a moving proposal and client availability changes separately. Runtime claims are checked against the WebMCP draft, Chrome implementation guidance and a real Chrome run. ChatGPT API-subset and model/workspace claims are checked against the official OpenAI Site tools page.

WebMCP draft · Chrome WebMCP docs · OpenAI Site tools docs