xseek.io WebMCP audit

Name: xseek.io WebMCP audit
Creator: ora

Rescan

audited Aug 28, 2026in 6s

36/ 100

4 tools registered. Strongest in WebMCP use, weakest in human experience.

WebMCP use66

Usefulness10

Human experience0

about:blank

No agent run recorded yet.

No steps recorded

Tools

/en

agent_ready_scan

Run an Agent-Ready scan on a public URL. Returns a readiness score plus per-check pass/fail breakdown (semantic HTML, schema markup, meta tags, content structure, accessibility for AI crawlers). Use this to check whether a page is well-structured enough for AI agents to cite.Takes an action on the site.

pagehttps://www.xseek.io/en

implementation

viaimperative

entry pointprovideContext

registered after859ms

executepresent

api surface

urlrequired

annotations

read onlynot declared

destructivenot declared

idempotentnot declared

open worldnot declared

untrusted contentnot declared

titlenot declared

3 findings

warningNaming quality

1 / 2

Tool naming makes selection harder than it needs to be: 4 names do not start with a verb (agent_ready_scan).

fix

{ name: "agent_ready_scan" /* short, unique, verb-based */ }

failAnnotations present

0 / 4

4 of 4 tools declare no readOnlyHint, so an agent cannot tell a read from a write without guessing from the name.

agent_ready_scan, llms_txt_scan, robots_txt_scan, contact_xseek

fix

{
  name: "agent_ready_scan",
  annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true }
}

warningHuman parity

0 / 8

4 of 4 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.

agent_ready_scan, llms_txt_scan, robots_txt_scan, contact_xseek

fix

<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="agent_ready_scan" tooldescription="...">
  <!-- the same action, as UI -->
</form>

tool json

{
  "name": "agent_ready_scan",
  "description": "Run an Agent-Ready scan on a public URL. Returns a readiness score plus per-check pass/fail breakdown (semantic HTML, schema markup, meta tags, content structure, accessibility for AI crawlers). Use this to check whether a page is well-structured enough for AI agents to cite.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "url": {
        "type": "string",
        "format": "uri",
        "description": "Absolute URL of the page to scan, e.g. https://example.com/about"
      }
    },
    "required": [
      "url"
    ]
  },
  "annotations": {}
}

Findings

WebMCP use

66 / 100 · weight 50

passTools registered

4 / 4

4 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 859ms of navigation.

toolllms_txt_scan

passCanonical entry point

4 / 4

All 4 tools register on the canonical document.modelContext entry point.

passSchema validity

5 / 5

All 4 tools declare a structurally valid object input schema.

passSchema quality

4 / 4

All 4 tool schemas describe their parameters and stay within Chrome's size guidance.

passStub detection

5 / 5

All 4 tools declare an execute handler.

failAnnotations present

0 / 4

4 of 4 tools declare no readOnlyHint, so an agent cannot tell a read from a write without guessing from the name.

toolagent_ready_scan

agent_ready_scan, llms_txt_scan, robots_txt_scan, contact_xseek

fix

{
  name: "agent_ready_scan",
  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.

warningUntrusted content hint

0 / 2

1 of 1 tools look like they return text written by other people but declare no untrustedContentHint, so an agent will treat the response as the site speaking.

toolcontact_xseek

contact_xseek: user, email

fix

{ name: "contact_xseek", annotations: { untrustedContentHint: true } }

passRegistration errors

2 / 2

No tool registration threw during the capture.

warningToolchange coherence

1 / 2

4 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

10 / 100 · weight 30

warningNaming quality

1 / 2

Tool naming makes selection harder than it needs to be: 4 names do not start with a verb (agent_ready_scan).

toolagent_ready_scan

fix

{ name: "agent_ready_scan" /* 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.

failCoverage vs. site type

0 / 8

The tool set covers 0 of the 4 things an agent needs on a saas site; it cannot search or browse the catalog or read one item in detail or create a record or start a job or update or move an existing record.

Human experience

0 / 100 · weight 20

warningHuman parity

0 / 8

toolagent_ready_scan

agent_ready_scan, llms_txt_scan, robots_txt_scan, contact_xseek

fix

<!-- Give the tool a visible counterpart: a declarative form is one the person can see and use too. -->
<form toolname="agent_ready_scan" 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: 4
run time: 6s
finished: Aug 28, 2026