agent-ready.dev WebMCP audit

Rescan
audited Aug 28, 2026in 4s
50/ 100

3 tools registered. Strongest in usefulness, weakest in human experience.

WebMCP use60
Usefulness67
Human experience0
about:blank

No agent run recorded yet.

No steps recorded

Tools

/
scan_site: fail

scan_site

Scan a public website for AI agent-readability against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol manifests. Returns a 0–100 score, the llms.txt score, and the top failing checks with a link to the full per-check report.Takes an action on the site.
pagehttps://agent-ready.dev/
implementation
viaimperative
entry pointnavigator
registered after304ms
executepresent
api surface
urlrequired
annotations
read onlynot declared
destructivenot declared
idempotentnot declared
open worldnot declared
untrusted contentnot declared
titlenot declared
4 findings
failCanonical entry point
0 / 4
Every tool registers through the deprecated navigator.modelContext alias; move them to document.modelContext before the alias is removed.
fix
// Use the canonical entry point - navigator.modelContext is deprecated.
document.modelContext.provideContext({ tools: [/* ... */] });
warningNaming quality
1.3 / 2
Tool naming makes selection harder than it needs to be: 2 names do not start with a verb (scan_site).
fix
{ name: "scan_site" /* short, unique, verb-based */ }
failAnnotations present
0 / 4
3 of 3 tools declare no readOnlyHint, so an agent cannot tell a read from a write without guessing from the name.
scan_site, get_scan, ask
fix
{
  name: "scan_site",
  annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true }
}
warningHuman parity
0 / 8
3 of 3 tools run through the JavaScript API with no visible counterpart, so the person co-browsing cannot see what the agent is offered. Declarative forms (or at least a title annotation) close the gap.
scan_site, get_scan, ask
fix
<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="scan_site" tooldescription="...">
  <!-- the same action, as UI -->
</form>
tool json
{
  "name": "scan_site",
  "description": "Scan a public website for AI agent-readability against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol manifests. Returns a 0–100 score, the llms.txt score, and the top failing checks with a link to the full per-check report.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "url": {
        "type": "string",
        "description": "The public URL to scan, e.g. https://example.com"
      }
    },
    "required": [
      "url"
    ],
    "additionalProperties": false
  },
  "annotations": {}
}
Showing scan_site

Findings

WebMCP use

60 / 100 · weight 50
passTools registered
4 / 4
3 tools registered across 1 page.
failReal-browser eligible
0 / 8
The page's code registers these tools, but a real visitor's browser does not get them yet: WebMCP needs a native modelContext or a current origin trial token, and this page has neither.
passRegistration timing
4 / 4
Every measured tool registered within 303.89999985694885ms of navigation.
toolask
failCanonical entry point
0 / 4
Every tool registers through the deprecated navigator.modelContext alias; move them to document.modelContext before the alias is removed.
toolscan_site
fix
// Use the canonical entry point - navigator.modelContext is deprecated.
document.modelContext.provideContext({ tools: [/* ... */] });
passSchema validity
5 / 5
All 3 tools declare a structurally valid object input schema.
passSchema quality
4 / 4
All 3 tool schemas describe their parameters and stay within Chrome's size guidance.
passStub detection
5 / 5
All 3 tools declare an execute handler.
failAnnotations present
0 / 4
3 of 3 tools declare no readOnlyHint, so an agent cannot tell a read from a write without guessing from the name.
toolscan_site
scan_site, get_scan, ask
fix
{
  name: "scan_site",
  annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true }
}
not applicableAnnotation mismatch
0 / 3
No tool declares a readOnlyHint, so there is no safety claim to contradict.
not applicableUntrusted content hint
0 / 2
No tool's contract suggests it returns text written by somebody other than the site, so there is nothing to flag as untrusted.
passRegistration errors
2 / 2
No tool registration threw during the capture.
warningToolchange coherence
1 / 2
3 tools were registered but the page never dispatched a toolchange event, so an agent subscribed to registry updates never learns they exist.
fix
document.modelContext.dispatchEvent(new Event("toolchange"));
not applicableInjection surface
0 / 3
The injection-surface model hop returned no usable result, so tool contracts were not reviewed for injection surface.

Usefulness

67 / 100 · weight 30
warningNaming quality
1.3 / 2
Tool naming makes selection harder than it needs to be: 2 names do not start with a verb (scan_site).
toolscan_site
fix
{ name: "scan_site" /* short, unique, verb-based */ }
not applicableDescription quality
0 / 6
The description-quality model hop returned no usable result, so descriptions were not rated.
not applicableTool selection
0 / 14
The tool-selection model hop returned no usable result.
not applicableCoverage vs. site type
0 / 8
This tool set does not place the site in a category with a known expected tool shape, so there is no coverage baseline to score it against.

Human experience

0 / 100 · weight 20
warningHuman parity
0 / 8
3 of 3 tools run through the JavaScript API with no visible counterpart, so the person co-browsing cannot see what the agent is offered. Declarative forms (or at least a title annotation) close the gap.
toolscan_site
scan_site, get_scan, ask
fix
<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="scan_site" tooldescription="...">
  <!-- the same action, as UI -->
</form>
not applicablePage experience
0 / 12
The page-experience model hop returned no usable result, so the page was not graded.

Tool selection

The tool-selection model hop returned no usable result.
how this was captured
chrome
148.0.7778.96
capture shim
v1
spec snapshot
2026-08
mode
fast
pages
1
tools
3
run time
4s
finished
Aug 28, 2026