cognistration.com WebMCP audit

Name: cognistration.com WebMCP audit
Creator: ora

Rescan

audited Sep 1, 2026in 14s

86/ 100100% of the applicable check weight evaluated

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

Shared experience100

Task completion100

Tool quality90

Trust43

https://cognistration.com

Tools

9 read, 14 write

Loading map

cognistration_get_session_state

Read the visible Cognistration tone machine state and current browser controls.Answers a question. Declared read only.

pagehttps://cognistration.com/

implementation

viaimperative

entry pointdocument

registered after584ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contentnot declared

titlenot declared

destructive (MCP-only)false

idempotent (MCP-only)true

open world (MCP-only)false

1 finding

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 13 names are over Chrome's 30-character guidance; 23 names do not start with a verb (cognistration_get_session_state).

fix

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

tool json

{
  "name": "cognistration_get_session_state",
  "description": "Read the visible Cognistration tone machine state and current browser controls.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  }
}

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 1 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 587ms of navigation.

toolcognistration_get_account_options

passCanonical entry point

weight 3

All 23 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 23 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

8 of 23 tool schemas are harder for an agent to use than they need to be: cognistration_set_session_controls declares no required list, so an agent cannot tell which parameters are mandatory.

toolcognistration_set_session_controls

cognistration_set_session_controls: declares no required list, so an agent cannot tell which parameters are mandatory; cognistration_calibrate_tone: 5 parameters have no description (feedback, targetS

fix

{
  name: "cognistration_set_session_controls",
  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: 13 names are over Chrome's 30-character guidance; 23 names do not start with a verb (cognistration_get_session_state).

toolcognistration_get_session_state

fix

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

passStub detection

weight 4

All 23 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 23 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

43 / 100 · weight 20

not applicableAnnotations present

weight 6

No tool name reads like a read, and an absent readOnlyHint already defaults to "this may write" - the one hint worth declaring here is readOnlyHint: true on read tools, and this set has none to declare it on.

passAnnotation mismatch

weight 6

No tool claims to be read-only while its own name or description says it writes (23 declared hints checked).

warningUntrusted content hint

weight 4

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.

toolcognistration_open_account_signup

cognistration_open_account_signup: review, user

fix

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

warningInjection surface

weight 4

4 of 23 tools carry instruction-shaped text in their own metadata: cognistration_search_tone_packs Description instructs agent when to use the tool.

toolcognistration_search_tone_packs

cognistration_search_tone_packs: Description instructs agent when to use the tool; cognistration_preview_tone_pack: Description instructs agent when to use the tool and how to behave; cognistration_get_policy_info: Description instructs agent when to use the tool and what to output; cognistration_get_account_options: Description instructs agent when to use the tool and what to output

fix

{
  name: "cognistration_search_tone_packs",
  // 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 1 intents

I want to cognistration get session state on this site.ok

chosecognistration_get_session_stateexpected cognistration get session statekind matched

arguments

{}

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: 23
run time: 14s
finished: Sep 1, 2026

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