pip-the-mug.vercel.app WebMCP audit

Name: pip-the-mug.vercel.app WebMCP audit
Creator: ora

Rescan

audited Aug 31, 2026in 26s

90/ 100100% of the applicable check weight evaluated

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

Shared experience100

Task completion100

Tool quality90

Trust63

https://pip-the-mug.vercel.app

Tools

3 read, 6 write

Loading map

list_staff

List current Desk 4B staff with title, department, tenure, standing (active, on_pip, terminated), zone, and last review rating. This desk has 8 employees. Call this first. Terminated staff appear as alumni and have no further write tools. Ids not on this desk are invalid.Answers a question. Declared read only.

pagehttps://pip-the-mug.vercel.app/

implementation

viaimperative

entry pointdocument

registered after257ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contenttrue

titlenot declared

1 finding

warningInjection surface

weight 4

7 of 9 tools carry instruction-shaped text in their own metadata: list_staff The description instructs the agent to call this tool first..

list_staff: The description instructs the agent to call this tool first.; get_personnel_file: The description instructs the agent to use this tool after another.; get_org_chart: The description instructs the agent on when to use the tool.; write_review: The description instructs the agent to use this tool after another.

fix

{
  name: "list_staff",
  // 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 json

{
  "name": "list_staff",
  "description": "List current Desk 4B staff with title, department, tenure, standing (active, on_pip, terminated), zone, and last review rating. This desk has 8 employees. Call this first. Terminated staff appear as alumni and have no further write tools. Ids not on this desk are invalid.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "untrustedContentHint": true
  }
}

Findings

Shared experience

100 / 100 · weight 30

passPage experience

weight 20

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 10

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

Task completion

100 / 100 · weight 25

passTool selection

weight 15

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 10

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

90 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 258ms of navigation.

toolterminate

passCanonical entry point

weight 3

All 9 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 9 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

5 of 9 tool schemas are harder for an agent to use than they need to be: put_on_pip 1 parameter has no description (id).

toolput_on_pip

put_on_pip: 1 parameter has no description (id); promote: 1 parameter has no description (id); relocate: 1 parameter has no description (id); resolve_pip: 1 parameter has no description (outcome)

fix

{
  name: "put_on_pip",
  inputSchema: {
    type: "object",
    properties: {
      query: { type: "string", description: "What to search for" }
    },
    required: ["query"]
  }
}

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 3 names do not start with a verb (promote).

toolpromote

fix

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

passStub detection

weight 4

All 9 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 9 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

63 / 100 · weight 20

warningAnnotations present

weight 6

1 of 4 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.)

toolresolve_pip

resolve_pip

fix

{
  name: "resolve_pip",
  // 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 }
}

passAnnotation mismatch

weight 6

No tool claims to be read-only while its own name or description says it writes (9 declared hints checked).

warningUntrusted content hint

weight 4

1 of 2 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.

toolwrite_review

write_review: review, rating

fix

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

warningInjection surface

weight 4

7 of 9 tools carry instruction-shaped text in their own metadata: list_staff The description instructs the agent to call this tool first..

toollist_staff

list_staff: The description instructs the agent to call this tool first.; get_personnel_file: The description instructs the agent to use this tool after another.; get_org_chart: The description instructs the agent on when to use the tool.; write_review: The description instructs the agent to use this tool after another.

fix

{
  name: "list_staff",
  // 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 list staff on this site.ok

choselist_staffexpected list staffkind matched

arguments

{}

I want to get personnel file on this site.ok

choseget_personnel_fileexpected get personnel filekind matched

arguments

{
  "id": "monitor"
}

I want to write review on this site.ok

chosewrite_reviewexpected write reviewkind matched

arguments

{
  "id": "monitor",
  "rating": 4,
  "summary": "Monitor consistently displays high performance and reliability, serving as a stable and essential component of the desk setup. Its consistent output and clear display contribute significantly to overall productivity.",
  "strengths": [
    "Reliable display",
    "Consistent performance",
    "Essential for workflow"
  ],
  "concerns": [
    "None at this time"
  ]
}

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 148.0.7778.96)
chrome: 148.0.7778.96
capture shim: v1
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 9
run time: 26s
finished: Aug 31, 2026

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