Runs your page in a real browser. No guessing. Blog Leaderboard RO EN
100/ 100

pcalba.ro A+

This site registers real WebMCP tools at runtime. Overall readiness is excellent.

Scanned 14 hours ago with Chrome 150, real execution with a modelContext interceptor and synthetic interaction. Scan another site

Agent access30 / 30
PASS Page loads over HTTPS 10/10 pts
The page answered with HTTP 200 over HTTPS.
PASS AI agents allowed in robots.txt 8/8 pts
No major AI crawler is blocked in robots.txt.
PASS llms.txt present 6/6 pts
Found llms.txt (1,298 bytes).
PASS Not blocked by noindex 6/6 pts
No noindex directive found.
WebMCP tools, measured in a real browser50 / 50
We load the page in Chrome, intercept modelContext before any script runs and record what your page actually registers.
PASS WebMCP tools detected at runtime 20/20 pts
3 tool(s) registered through modelContext.registerTool() while the page ran in our Chrome.
PASS Tool schema quality 15/15 pts
Average schema quality 5/5 across 3 tool(s).
PASS Origin Trial token 15/15 pts
Valid WebMCP token for pcalba.ro, expires 17 Nov 2026.
Discovery, community conventions20 / 20
Not part of the official Chrome spec. Scored as a small bonus because static crawlers and directories use it.
PASS Discovery manifest at /.well-known/webmcp 10/10 pts
Valid JSON manifest found.
PASS Manifest describes tools 5/5 pts
3 tool(s) described in the manifest.
PASS Manifest served as application/json 5/5 pts
Content-Type is application/json.

Tools registered by this page

NameDescriptionParametersRead-only
validate_website Start a WebMCP validation scan for a public website; returns the report link (the scan com... 1 no
get_webmcp_report Get the latest completed WebMCP validation report (score, grade, per-check results) for a... 1 yes
get_leaderboard Get the leaderboard (top scoring websites) from the WebMCP Validator with scores, grades a... 1 yes

Captured live from modelContext.registerTool() calls while the page ran. A static HTML scan cannot see these.

Not measurable remotely, so not scored: end-to-end tool execution by an agent, human-in-the-loop consent handling, and result quality. Test those with the Model Context Tool Inspector extension in a WebMCP-capable Chrome.

Push this score higher?

GOAI implements WebMCP end to end: imperative tools, valid schemas, the origin trial token and the discovery manifest.

Talk to GOAI