threatcanvas-webmcp.alx21.chatgpt.site WebMCP audit

Name: threatcanvas-webmcp.alx21.chatgpt.site WebMCP audit
Creator: ora

Rescan

audited Sep 1, 2026in 20s

68/ 100100% of the applicable check weight evaluated

14 tools registered. Strongest in shared experience, weakest in task completion.

Shared experience100

Task completion13

Tool quality87

Trust63

https://threatcanvas-webmcp.alx21.chatgpt.site

Tools

4 read, 10 write

Loading map

list_findings

List findings in the active ThreatCanvas workspace, optionally filtered by severity, status, component, tag, or minimum priority. Use this to triage the board before inspecting or changing individual findings.Answers a question. Declared read only.

pagehttps://threatcanvas-webmcp.alx21.chatgpt.site/

implementation

viaimperative

entry pointdocument

registered after724ms

executepresent

api surface

severityoptional

statusoptional

componentoptional

tagoptional

minimumPriorityoptional

limitoptional

annotations

read onlytrue

untrusted contenttrue

titlenot declared

2 findings

warningSchema quality

weight 4

10 of 14 tool schemas are harder for an agent to use than they need to be: list_findings 6 parameters have no description (severity, status, component, tag).

list_findings: 6 parameters have no description (severity, status, component, tag); set_finding_severity: 1 parameter has no description (severity); set_finding_status: 1 parameter has no description

fix

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

warningInjection surface

weight 4

8 of 14 tools carry instruction-shaped text in their own metadata: list_findings Description instructs the agent when to use the tool..

list_findings: Description instructs the agent when to use the tool.; inspect_finding: Description instructs the agent when to use the tool.; set_finding_severity: Description instructs the agent when to use the tool.; set_finding_status: Description instructs the agent when to use the tool and what to include.

fix

{
  name: "list_findings",
  // 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_findings",
  "description": "List findings in the active ThreatCanvas workspace, optionally filtered by severity, status, component, tag, or minimum priority. Use this to triage the board before inspecting or changing individual findings.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "severity": {
        "type": "string",
        "enum": [
          "critical",
          "high",
          "medium",
          "low"
        ]
      },
      "status": {
        "type": "string",
        "enum": [
          "open",
          "investigating",
          "accepted",
          "scheduled",
          "resolved"
        ]
      },
      "component": {
        "type": "string",
        "maxLength": 120
      },
      "tag": {
        "type": "string",
        "maxLength": 60
      },
      "minimumPriority": {
        "type": "number",
        "minimum": 0,
        "maximum": 100
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 50
      }
    },
    "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

13 / 100 · weight 25

failTool selection

weight 15

An agent chose an existing tool and built a schema-valid call that held up on 0 of 3 canonical intents; on "Open the document I was working on most recently." no tool on the page served it. Nothing was executed, so this verifies selection, not outcomes.

failCoverage vs. site type

weight 10

The tool set covers 1 of the 3 things an agent needs on a editor site; it cannot edit or write content or save, publish, or share the result.

Tool quality

87 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 725ms of navigation.

toolmark_finding_human_locked

passCanonical entry point

weight 3

All 14 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 14 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

10 of 14 tool schemas are harder for an agent to use than they need to be: list_findings 6 parameters have no description (severity, status, component, tag).

toollist_findings

list_findings: 6 parameters have no description (severity, status, component, tag); set_finding_severity: 1 parameter has no description (severity); set_finding_status: 1 parameter has no description

fix

{
  name: "list_findings",
  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: 4 names do not start with a verb (inspect_finding).

toolinspect_finding

fix

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

passStub detection

weight 4

All 14 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 14 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.)

toolcompare_findings

compare_findings

fix

{
  name: "compare_findings",
  // 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 (14 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.

toolreset_demo_workspace

reset_demo_workspace: note, user, rating

fix

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

warningInjection surface

weight 4

8 of 14 tools carry instruction-shaped text in their own metadata: list_findings Description instructs the agent when to use the tool..

toollist_findings

list_findings: Description instructs the agent when to use the tool.; inspect_finding: Description instructs the agent when to use the tool.; set_finding_severity: Description instructs the agent when to use the tool.; set_finding_status: Description instructs the agent when to use the tool and what to include.

fix

{
  name: "list_findings",
  // 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

0% across 3 intents

Open the document I was working on most recently.missed

choseno toolexpected document openkind not applicable

No tool was picked for this intent.

arguments

{}

Add a short summary paragraph at the top.missed

choseno toolexpected content editkind not applicable

No tool was picked for this intent.

arguments

{}

Save it and give me a link I can share.missed

choseno toolexpected save or sharekind not applicable

No tool was picked for this intent.

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: v2
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 14
run time: 20s
finished: Sep 1, 2026

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