For consultants, agencies, and operators preparing client sites for agentic traffic
Know whether a client page is ready for agents
Get an actionable, detailed review and build plan for making any public page ready for AI agents, based on your content, not generalized advice. Point the eval at one public URL and you see the tools the page already registers and whether to keep, rename or fix them, the tools to add (each tied to a link or form on the page), and what must never be exposed (checkout, place-order, anything irreversible).
First evaluation free — no card. On the connector consent page, choose Try one free evaluation. One per person. The $26 starter below is the paid pack.
Free scanners give you a score. This gives your agent the build list — so the next step in the same conversation is the registration code, not a meeting about what the score means. Built for people who sit between a client website and the agents that will soon arrive uninvited.
- Name the page. A services page, an audit offer, a product URL — one address.
- Read the verdict. Capability, page intent, tools observed, tools recommended, do-not-expose list.
- Brief the client. What to publish in WebMCP, what to keep human-only, what is already fine.
One result, wherever you work
Results your agent can act on
Every evaluation comes back with the same structured results. Each recommended tool carries its input schema, a relation (keep, rename, fix_description, new, needs_owner_input) and the evidence it rests on: the page, the link or form, and the HTTP status. The result also says what was checked and what was not.
In Claude or ChatGPT
Ask for the evaluation, then keep going: “write the WebMCP registration code for the ready offers” or “brief the client in plain English”. The model works from the plan, not from a guess at the DOM.
In your own app
Store results per client page, compare runs before and after a build, or feed your own reports and dashboards. Review the sample for the fields and data provided to your favorite model or custom app.
From a CLI or CI
Any MCP client with a Bearer usr_live_… header can call it — Claude Code, Cursor, or a script. Re-check client pages on a schedule and flag a build when a registered tool comes back fix_description or needs_owner_input. Setup.
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, checked, not_checked, and do_not_expose.
What you should see on that URL:
- Intent:
intake— the page object is the audit conversation, not an essay. - Purpose / CTA: object is the audit; CTA is book or start. Catalog tools on the property are context, not the job of this URL.
- Capability:
polyfillwhen the page registers tools;not_detectedwhen it does not. Never “none.” - Recommend: plans and process as answers, tied to a link, form, registered tool, or published price on the page. At most one book or start act. An existing tool is recognized: keep it, rename it to the registered name, or fix the description.
- Evidence: each finding shows the page it came from. The report says what was checked and what was not.
- Do not expose:
place_order,submit_payment, card capture.
$2 when that call is billed: the page loads and the analysis runs. The agent returns structured results — see a full sample result and the human brief (print to PDF). Connect Claude, ChatGPT, or Grok.
Starter pack — $26
First evaluation free — no card. This box is the paid starter: $26 for 13 evaluations.
$26 13 evaluations
- $2 per billed evaluation (the page loads and the analysis runs)
- Credit lives on the key we send you
- This button mints a new key. Already connected? Call unpaid
reload_creditsin the host — that $26 credits the same key.
Pay $26 on Stripe (card or Link). This page sends you to Checkout and comes back with a new usr_live_ to paste. A second click here is a second wallet; leftover on an old key stays there. If the evaluator is already connected and the wallet is empty, do not buy here — use reload_credits so the connector does not change.
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
Not billed if the page doesn't load (no 2xx response) or neither page rendering nor model analysis succeeds. You still get the result, marked billed: false, and the $2 goes back to your balance.
Custom eval kits are available for larger volumes.
First evaluation free
First evaluation free — no card. One per person. On a connector consent page, choose Try one free evaluation.
ChatGPT Business, Cursor, and other hosts without a consent page: email [email protected] for a one-time pass link.
Connect Claude.ai, ChatGPT, or Grok
Same URL everywhere: https://mcp.webmcp-eval.com/mcp. Claim one free evaluation, or buy a key, then add the connector and paste the example prompt above. Every /mcp call needs a key or an OAuth token. With a key, get_credits is not billed. Only a billed evaluate_webmcp is $2. Results that come back billed: false cost nothing.
- Claude.ai — Add WebMCP Evaluator from the Claude directory (verified by Anthropic), then Connect. On our consent page, choose Try one free evaluation or paste
usr_live_. - ChatGPT — Plus: Developer mode + OAuth. Business Workspace: admin publishes the App as a Bearer API key; member pastes
usr_live_. - Grok — custom connector, same URL; OAuth or
Authorization: Bearer usr_live_….
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. Privacy.