webmcp-eval

For consultants preparing client sites for agentic traffic

Know whether a client page is ready for agents — before you promise it is.

Point the eval at one public URL. You get a readiness reading: can an agent use this page as tools, what is already registered, what to add, and what must never be exposed (checkout, place-order, anything irreversible).

Built for people who sit between a client website and the agents that will soon arrive uninvited. Not a scrape dump. Not a Lighthouse score.

  1. Name the page. A services page, an audit offer, a product URL — one address.
  2. Read the verdict. Capability, page intent, tools observed, tools recommended, do-not-expose list.
  3. Brief the client. What to publish in WebMCP, what to keep human-only, what is already fine.

Worked example

Say this in Claude.ai or ChatGPT

Evaluate https://www.sunbusinessgroup.com/ai/ai-audit.html with evaluate_webmcp.
Return page_intent, recommended_offers, and do_not_expose.

What you should see on that URL:

$2 when that call completes. The agent returns JSON — render the human brief (print to PDF). Connect Claude, ChatGPT, or Grok.

Who this is for

  • Consultants standing up WebMCP on a client property
  • Agencies that need a repeatable readiness pass before a build
  • Operators who want agents to book and answer — not wander the DOM

Failed fetches are not billed.

Connect Claude.ai, ChatGPT, or Grok

Same URL everywhere: https://mcp.webmcp-eval.com/mcp. Buy a key, add the connector, paste the example prompt above.

Full steps, Cursor snippet, and 401 checklist.

Pages we fetch, and their public HTML, may go to our subprocessor (Firecrawl) so JavaScript-rendered sites can be read. Do not send secrets or private URLs. Terms.