agentdom-one.vercel.app WebMCP audit

Name: agentdom-one.vercel.app WebMCP audit
Creator: ora

Rescan

audited Sep 1, 2026in 12s

100/ 100100% of the applicable check weight evaluated

14 tools registered. Strongest in shared experience, weakest in tool quality.

Shared experience100

Task completion100

Tool quality99

Trust100

https://agentdom-one.vercel.app

Tools

8 read, 6 write

Loading map

list_documents

Lists every local note (document) the user has, most recently updated first. Use this to see what documents exist. Returns, for each document, only its id, title, a short one-line preview, tags, and last-updated time — never the full document body. Does NOT open or select a document; call open_document with the id you want next.Answers a question. Declared read only.

pagehttps://agentdom-one.vercel.app/

implementation

viaimperative

entry pointdocument

registered after178ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contenttrue

titlenot declared

idempotent (MCP-only)true

0 findingsNo check named this tool.

tool json

{
  "name": "list_documents",
  "description": "Lists every local note (document) the user has, most recently updated first. Use this to see what documents exist. Returns, for each document, only its id, title, a short one-line preview, tags, and last-updated time — never the full document body. Does NOT open or select a document; call open_document with the id you want next.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "idempotentHint": 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.

passCoverage vs. site type

weight 10

The tool set covers the whole core editor flow: open or read a document, edit or write content, save, publish, or share the result.

Tool quality

99 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 179ms of navigation.

toolreject_link_suggestion

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.

passSchema quality

weight 4

All 10 of 14 tool schemas that declare parameters describe them (the other 4 declare no parameters), and every description stays within Chrome's size guidance.

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 5 names do not start with a verb (open_document).

toolopen_document

fix

{ name: "open_document" /* 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

100 / 100 · weight 20

passAnnotations present

weight 6

All 6 read-shaped tools declare readOnlyHint: true - the one declared claim that lets an agent treat a call as safe to make without asking.

passAnnotation mismatch

weight 6

No tool claims to be read-only while its own name or description says it writes (14 declared hints checked).

passUntrusted content hint

weight 4

All 2 tools that look like they return third-party text declare untrustedContentHint.

not applicableInjection surface

weight 4

No tool's metadata carries instruction-shaped text aimed at the agent reading it. This check only ever flags; it never credits a site.

Tool selection

100% across 3 intents

Open the document I was working on most recently.ok

choseopen_documentexpected document openkind matched

arguments

{}

Add a short summary paragraph at the top.ok

choseinsert_paragraphexpected content editkind matched

arguments

{
  "text": "This is a short summary paragraph.",
  "position": "top"
}

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

chosecreate_share_linkexpected save or sharekind 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: 14
run time: 12s
finished: Sep 1, 2026

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