WebMCP Validator for AI Agent Tools avatar

WebMCP Validator for AI Agent Tools

Pricing

from $7.48 / 1,000 webmcp validation reports

Go to Apify Store
WebMCP Validator for AI Agent Tools

WebMCP Validator for AI Agent Tools

Check whether any public URL is ready for AI agents that speak WebMCP. Open the page, capture registered tools, declarative HTML forms, Cloudflare WebMCP packs, and MCP catalogs, then get a 0–100 readiness score with pass, warn, and fail checks. No login. Export JSON, CSV, or Excel.

Pricing

from $7.48 / 1,000 webmcp validation reports

Rating

0.0

(0)

Developer

rainminer

rainminer

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

9 days ago

Last modified

Share

MCP logo

WebMCP Validator

WebMCP Validator

WebMCP Validator opens any public URL and reports whether the page is ready for AI agents that speak WebMCP. It records tools registered on document.modelContext, declarative toolname forms, Cloudflare WebMCP packs, and MCP HTTP catalogs, then returns a readiness score with pass / warn / fail checks.

Try it on the public Chrome Labs demo: WebMCP explainer.

Need a flat catalog instead of a scorecard? Use WebMCP Scraper for one row per tool, resource, or prompt.


What does WebMCP Validator do?

WebMCP (Web Model Context Protocol) lets a website declare agent tools in the page — names, descriptions, and JSON schemas — so an in-browser agent can call bookSlot instead of guessing at buttons. Chrome is shipping the API as document.modelContext. Cloudflare can inject a same-origin WebMCP pack that registers those tools for you.

This Actor:

  1. Opens each start URL in a headless browser
  2. Captures registerTool calls as the page boots
  3. Reads declarative HTML form tools (toolname, tooldescription)
  4. Detects Cloudflare WebMCP packs and advertised MCP catalog URLs
  5. Optionally lists tools, resources, and prompts from the site’s MCP HTTP endpoint
  6. Scores agent-readiness and lists concrete issues

Run it on Apify to schedule audits, monitor regressions, and export reports via API.


Why validate WebMCP?

Agent traffic is growing, but most sites still only offer a human UI. Use this Actor when you need to know, at scale, whether a URL actually exposes a machine-usable tool surface:

  • Ship-check a WebMCP implementation before you announce agent support
  • CI / monitoring for pages that must keep tools registered
  • Competitive audits of who already exposes agent tools
  • Cloudflare pack QA after turning on WebMCP in the dashboard
  • Schema review so tool names and JSON schemas match the spec
  • Migration from deprecated navigator.modelContext to document.modelContext
  • Directory ops that only list sites with a passing readiness score
  • Security review of which tools a public page advertises
  • MCP catalog health for advertised MCP HTTP endpoints
  • Agency reporting for clients adopting agent-ready websites
  • Product research on WebMCP adoption across a URL list
  • Incident response when an agent integration suddenly sees zero tools

How to validate WebMCP on a website

  1. Open the Actor in Apify Console
  2. Paste one or more page URLs (homepages or specific app screens)
  3. Keep Probe MCP HTTP catalog on unless you only want in-page tools
  4. Increase Extra wait time for slow single-page apps
  5. Click Start and open the dataset Overview

You can also call the Actor from the Apify API, webhooks, or a schedule. Pair it with WebMCP Scraper when a failing score should dump the full tool catalog for debugging.

Input example

{
"startUrls": [
{ "url": "https://googlechromelabs.github.io/webmcp-tools/demos/explainer/" }
],
"maxItems": 5,
"waitUntil": "networkidle",
"waitForMillis": 4000,
"probeMcpHttp": true,
"proxyConfiguration": {
"useApifyProxy": false
}
}

Output

Each start URL produces one dataset row: readiness (ready, partial, or not_detected), a 0–100 score, tool / resource / prompt counts, and the full check list.

{
"url": "https://googlechromelabs.github.io/webmcp-tools/demos/explainer/",
"finalUrl": "https://googlechromelabs.github.io/webmcp-tools/demos/explainer/",
"pageTitle": "WebMCP — Give agents tools, not DOM",
"isWebMcpEnabled": true,
"readiness": "ready",
"score": 100,
"summary": "WebMCP looks ready (3 tool source(s) found, score 100).",
"toolCount": 3,
"resourceCount": 0,
"promptCount": 0,
"cloudflareBridge": false,
"mcpHttpOk": false,
"usesDocumentApi": true,
"usesDeprecatedNavigatorApi": false,
"checks": [
{
"id": "tools-registered",
"title": "Tools registered",
"status": "pass",
"message": "Captured 3 tool(s) via registerTool."
}
],
"issues": [],
"warnings": []
}

Download the dataset as JSON, CSV, or Excel. The Overview tab highlights the score, tool counts, and page image when Open Graph provides one.


How much does it cost?

This Actor uses pay-per-event pricing. Platform compute is included in the event price — you are not billed extra Playwright usage.

EventFREE plan
Actor start$0.00005
Validation report (one per start URL)$9.99 / 1,000 ($0.00999 each)

Paid Apify Store plans get volume discounts (GOLD from $7.48 / 1,000). No proxy is required by default. A 20-URL audit is about $0.20 in event fees on FREE. Check the Pricing tab for current rates.


FAQ

What is WebMCP?

WebMCP is a W3C Web Machine Learning Community Group API. Pages register tools with document.modelContext.registerTool(), each with a name, description, JSON Schema, and an execute handler. Agents discover those tools instead of scraping the DOM. See the explainer and Cloudflare’s WebMCP preview.

Does the target site need the latest Chrome?

No. The Actor captures tool registration even when the crawler browser has no native WebMCP surface, so you can audit sites that already call document.modelContext.

Will it log in?

No. Only public pages. Cookie banners and bot challenges are fine; account login is not supported.

Does it execute tools?

No. It only detects and scores registered tools. It does not call execute handlers or MCP tools/call.

ActorJob
WebMCP ScraperOne dataset row per tool, resource, or prompt
WebMCP ValidatorPer-URL readiness score and spec checks (this Actor)

Open an issue on the Actor page if a public demo URL stops scoring. Feature requests for extra checks are welcome.


Image Credit

Logo and banner use the official Model Context Protocol mark from the MCP docs logo.