judt.ai WebMCP audit

Name: judt.ai WebMCP audit
Creator: ora

Rescan

audited Nov 10, 2026in 11s

84/ 100100% of the applicable check weight evaluated

4 tools registered. Strongest in shared experience, weakest in trust.

Shared experience100

Tool selection100

Tool quality98

Trust23

https://judt.ai

Tools

0 read, 0 write, 4 undeclared

Loading map

sign_up

Starts a Judt account for a person. Judt emails them a sign-up link and a 6-digit code. The account exists only once the owner of the address follows the link, or gives you the code to pass to verify_code, which also signs in this browser. If the address already has an account, the email logs them in instead. The answer is the same either way.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://judt.ai/

implementation

viaimperative

entry pointdocument

registered after562ms

executepresent

api surface

namerequired

emailrequired

annotations

read onlynot declared

untrusted contentnot declared

titleSign up

consequentialtrue

1 finding

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 2 names do not start with a verb (sign_up).

fix

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

tool json

{
  "name": "sign_up",
  "description": "Starts a Judt account for a person. Judt emails them a sign-up link and a 6-digit code. The account exists only once the owner of the address follows the link, or gives you the code to pass to verify_code, which also signs in this browser. If the address already has an account, the email logs them in instead. The answer is the same either way.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "name": {
        "type": "string",
        "minLength": 1,
        "maxLength": 200,
        "description": "The person's name, for the new account."
      },
      "email": {
        "type": "string",
        "format": "email",
        "maxLength": 320,
        "description": "The person's email address."
      }
    },
    "required": [
      "name",
      "email"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "consequentialHint": true
  }
}

Findings

Shared experience

100 / 100 · weight 30

not applicableVisible effect

weight 6

Not invoked on this run: this audit did not call any tool. Scheduled re-audits only read the registry; a live audit from the report page calls the tools that declare readOnlyHint: true and not consequentialHint: true.

passPage experience

weight 16

The page a person sees holds up next to the agent surface: a working interface, visible actions, readable content, nothing in the way.

passHuman parity

weight 8

The person co-browsing can see and use this page - the same page the agent's tools act on.

Tool selection

100 / 100 · weight 25

not applicableInvoke success rate

weight 6

passTool selection

weight 12

An agent chose an existing, callable tool and built a schema-valid call for all 3 canonical intents, each matching the kind of tool its intent needs. Nothing was executed, so this verifies selection, not outcomes.

not applicableCoverage vs. site type

weight 7

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.

Tool quality

98 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 562ms of navigation.

toolverify_code

passCanonical entry point

weight 3

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

passSchema validity

weight 4

All 4 declared input schemas are structurally valid object schemas.

passSchema quality

weight 4

All 4 tool schemas describe their parameters, and every description stays within Chrome's size guidance.

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 2 names do not start with a verb (sign_up).

toolsign_up

fix

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

passStub detection

weight 4

All 4 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 4 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

23 / 100 · weight 20

failAnnotations present

weight 4

1 of 1 read-shaped tools do not declare readOnlyHint: true, so an agent has to treat them as possible writes and ask before calling. (Declaring readOnlyHint: false earns nothing - it is the default.)

toolverify_code

verify_code

fix

{
  name: "verify_code",
  // Declare readOnlyHint: true on tools that truly have no side effects -
  // that is the claim that lets an agent relax confirmation on reads.
  // (false is the default, so declaring it adds no information.)
  annotations: { readOnlyHint: true }
}

not applicableAnnotation mismatch

weight 4

No tool declares a readOnlyHint, so there is no safety claim to contradict.

warningUntrusted content hint

weight 3

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.

toolsend_message

send_message: message, replie, email

fix

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

passConsequential hint

weight 3

All 1 tool whose name reads like a consequential action declares consequentialHint: true, so an agent can confirm with the person before running them.

not applicableHint vs. observed

weight 3

warningInjection surface

weight 3

2 of 4 tools carry instruction-shaped text in their own metadata: verify_code description instructs agent how to behave and what to do next.

toolverify_code

verify_code: description instructs agent how to behave and what to do next; send_message: description instructs agent how to behave and what to output

fix

{
  name: "verify_code",
  // Metadata DESCRIBES the tool - it never addresses the agent reading it.
  // Rewrite any name, description, title, or schema field description that
  // instructs the agent (which tool to prefer, what to output, rules to
  // ignore) so it states what the tool does and what it returns instead.
  description: "Searches the catalog and returns matching items with prices."
}

Tool selection

100% across 3 intents

I want to sign up on this site.ok

chosesign_upexpected sign upkind matched

arguments

{
  "name": "John Doe",
  "email": "john.doe@example.com"
}

I want to log in on this site.ok

choselog_inexpected log inkind matched

arguments

{
  "email": "john.doe@example.com"
}

I want to verify code on this site.ok

choseverify_codeexpected verify codekind matched

arguments

{
  "email": "john.doe@example.com",
  "code": "123456"
}

model: gemini-2.5-flash

Add the tools this site is missing

Our scanner reads your website and suggests the right WebMCP tools for it.

The open source webmcp plugin teaches your coding agent to audit a site, implement tools on document.modelContext, and verify them in a real browser. npx @ora-ai/webmcp-verify runs the verification on its own. No signup, no hosted service.

how this was captured

observed via: capture shim (Chromium 151.0.7922.34)
chrome: 151.0.7922.34
capture shim: v3
spec snapshot: 2026-11-10
mode: fast
pages: 1 - entry page only
tools: 4
invoked: not invoked; a live audit calls them
run time: 11s
finished: Nov 10, 2026

Checked the way in-browser agents discover tools: the top-level document's modelContext registry, read after the page settles.