webmcpworld.com WebMCP audit

Name: webmcpworld.com WebMCP audit
Creator: ora

Rescan

audited Nov 3, 2026in 25s

81/ 100100% of the applicable check weight evaluated

7 tools registered. Strongest in tool selection, weakest in trust.

Shared experience87

Tool selection100

Tool quality90

Trust36

https://webmcpworld.com

Tools

0 read, 7 write

Loading map

contact_us

Use this tool to submit the Contact Us. This form collects: Name, Email, Comment or Message.Takes an action on the site.

pagehttps://webmcpworld.com/

implementation

viaimperative

entry pointdocument

registered after4519ms

executepresent

api surface

namerequired

emailrequired

commentormessagerequired

annotations

read onlyfalse

untrusted contentfalse

titlenot declared

consequentialtrue

2 findings

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 1 name does not start with a verb (contact_us).

fix

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

warningUntrusted content hint

weight 3

2 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.

contact_us: comment, message, email; get_posts: post, user

fix

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

tool json

{
  "name": "contact_us",
  "description": "Use this tool to submit the Contact Us. This form collects: Name, Email, Comment or Message.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "name": {
        "type": "string",
        "title": "Name",
        "description": "First Name and Last Name Field"
      },
      "email": {
        "type": "string",
        "title": "Email",
        "description": "email",
        "format": "email"
      },
      "commentormessage": {
        "type": "string",
        "title": "Comment or Message",
        "description": "Add query or your message"
      }
    },
    "required": [
      "name",
      "email",
      "commentormessage"
    ]
  },
  "annotations": {
    "readOnlyHint": false,
    "untrustedContentHint": false,
    "consequentialHint": true
  }
}

Findings

Shared experience

87 / 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

1 of 4 page-experience marks came back short: readability Some text is very light against a dark background, making it hard to read..

readability: weak

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

90 / 100 · weight 25

failRegistration timing

weight 1

The slowest tool took 4628ms to register, past the 3000ms window an agent snapshots the registry in, so it may never be offered.

toolget_categories

get_categories: registered at 4628ms

fix

// Register tools as soon as they're ready, not behind a deferred/async chunk.
document.modelContext.registerTool({ /* ... */ });

passCanonical entry point

weight 3

All 7 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 7 declared input schemas are structurally valid object schemas.

warningSchema quality

weight 4

2 of 7 tool schemas are harder for an agent to use than they need to be: search_posts 3 parameters have no description (post_type, per_page, page).

toolsearch_posts

search_posts: 3 parameters have no description (post_type, per_page, page); get_categories: 3 parameters have no description (hide_empty, per_page, page)

fix

{
  name: "search_posts",
  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: 1 name does not start with a verb (contact_us).

toolcontact_us

fix

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

passStub detection

weight 4

All 7 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 7 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

36 / 100 · weight 20

failAnnotations present

weight 4

6 of 6 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.)

toolsearch_posts

search_posts, get_posts, get_post, get_site_info, get_categories

fix

{
  name: "search_posts",
  // 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 4

No tool claims to be read-only while its own name or description says it writes (7 declared hints checked).

warningUntrusted content hint

weight 3

2 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.

toolcontact_us

contact_us: comment, message, email; get_posts: post, user

fix

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

not applicableConsequential hint

weight 3

No tool name reads like a consequential action (a purchase, a booking, a payment, a transfer, a deletion), so there is no consequentialHint to expect.

not applicableHint vs. observed

weight 3

not applicableInjection surface

weight 3

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

I want to contact us on this site.ok

chosecontact_usexpected contact uskind matched

arguments

{
  "name": "John Doe",
  "email": "john.doe@example.com",
  "commentormessage": "I would like to contact you."
}

I want to search posts on this site.ok

chosesearch_postsexpected search postskind matched

arguments

{
  "query": ""
}

I want to get posts on this site.ok

choseget_postsexpected get postskind matched

arguments

{
  "post_type": "post"
}

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: 2026-10-16
mode: fast
pages: 1 - entry page only
tools: 7
invoked: not invoked; a live audit calls them
run time: 25s
finished: Nov 3, 2026

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