essentials.sh WebMCP audit

Name: essentials.sh WebMCP audit
Creator: ora

Rescan

audited Sep 1, 2026in 39s

69/ 100100% of the applicable check weight evaluated

7 tools registered. Strongest in tool quality, weakest in task completion.

Shared experience88

Task completion0

Tool quality95

Trust93

https://essentials.sh

Tools

7 read, 0 write

Loading map

generate_qr_code

Generate a QR code for a URL. Returns the QR code as an SVG document that can be rendered directly or saved as a .svg file. Runs locally in the browser; https:// is assumed when the URL has no scheme.Answers a question. Declared read only.

pagehttps://essentials.sh/

implementation

viaimperative

entry pointdocument

registered after775ms

executepresent

api surface

urlrequired

errorCorrectionoptional

annotations

read onlytrue

untrusted contentnot declared

titlenot declared

1 finding

warningAnnotation mismatch

weight 6

1 tool declares readOnlyHint: true although the name says the call writes (generate_qr_code).

generate_qr_code: readOnlyHint=true

fix

// readOnlyHint must match what the tool actually does - drop it (or set false) on a tool that writes.
{ name: "generate_qr_code", annotations: { readOnlyHint: false } }

tool json

{
  "name": "generate_qr_code",
  "description": "Generate a QR code for a URL. Returns the QR code as an SVG document that can be rendered directly or saved as a .svg file. Runs locally in the browser; https:// is assumed when the URL has no scheme.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "url": {
        "type": "string",
        "description": "The URL to encode"
      },
      "errorCorrection": {
        "type": "string",
        "enum": [
          "L",
          "M",
          "Q",
          "H"
        ],
        "description": "Error correction level: L ~7%, M ~15% (default), Q ~25%, H ~30% recoverable. Use H when overlaying a logo."
      }
    },
    "required": [
      "url"
    ]
  },
  "annotations": {
    "readOnlyHint": true
  }
}

Findings

Shared experience

88 / 100 · weight 30

passPage experience

weight 20

1 of 4 page-experience marks came back short: obstruction A cookie banner partially obscures content at the bottom of the page..

obstruction: weak

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

0 / 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 0 of the 3 things an agent needs on a editor site; it cannot open or read a document or edit or write content or save, publish, or share the result.

Tool quality

95 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 776ms of navigation.

toolcheck_email_security

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

1 of 7 tool schemas are harder for an agent to use than they need to be: build_robots_txt declares no required list, so an agent cannot tell which parameters are mandatory.

toolbuild_robots_txt

build_robots_txt: declares no required list, so an agent cannot tell which parameters are mandatory

fix

{
  name: "build_robots_txt",
  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: 5 names do not start with a verb (build_meta_tags).

toolbuild_meta_tags

fix

{ name: "build_meta_tags" /* 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

93 / 100 · weight 20

passAnnotations present

weight 6

All 1 read-shaped tool declares readOnlyHint: true - the one declared claim that lets an agent treat a call as safe to make without asking.

warningAnnotation mismatch

weight 6

1 tool declares readOnlyHint: true although the name says the call writes (generate_qr_code).

toolgenerate_qr_code

generate_qr_code: readOnlyHint=true

fix

// readOnlyHint must match what the tool actually does - drop it (or set false) on a tool that writes.
{ name: "generate_qr_code", annotations: { readOnlyHint: false } }

not applicableUntrusted content hint

weight 4

No tool's contract suggests it returns text written by somebody other than the site, so there is nothing to flag as untrusted.

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

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: native modelContext
chrome: 148.0.7778.96
capture shim: v2
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 7
run time: 39s
finished: Sep 1, 2026

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