pixeltable.com WebMCP audit

Name: pixeltable.com WebMCP audit
Creator: ora

Rescan

audited Sep 7, 2026in 12s

63/ 100100% of the applicable check weight evaluated

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

Shared experience100

Tool selection36

Tool quality96

Trust0

https://pixeltable.com

Tools

0 read, 0 write, 5 undeclared

Loading map

navigate_pixeltable

Navigate to a Pixeltable site page. Use for docs, pricing, blog, compare, waitlist, agent skill, or home.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://www.pixeltable.com/

implementation

viaimperative

entry pointdocument

registered after420ms

executepresent

api surface

pathrequired

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

1 finding

warningInjection surface

weight 3

1 of 5 tools carry instruction-shaped text in their own metadata: navigate_pixeltable Description instructs agent on tool usage and preference..

navigate_pixeltable: Description instructs agent on tool usage and preference.

fix

{
  name: "navigate_pixeltable",
  // 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": "navigate_pixeltable",
  "description": "Navigate to a Pixeltable site page. Use for docs, pricing, blog, compare, waitlist, agent skill, or home.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "path": {
        "type": "string",
        "description": "Site path starting with /, e.g. /pricing, /blog, /compare, /waitlist, /agent-skill, /get-started.md, /ask"
      }
    },
    "required": [
      "path"
    ]
  },
  "annotations": {}
}

Findings

Shared experience

100 / 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.

passPage experience

weight 16

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 8

The person co-browsing can see and use this page - the same page the agent's tools act on.

Tool selection

36 / 100 · weight 25

not applicableInvoke success rate

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.

failTool selection

weight 12

An agent chose an existing tool and built a schema-valid call that held up on 0 of 3 canonical intents; on "Find the page that explains authentication." the tool it chose does not look like the kind of tool the intent needs. Nothing was executed, so this verifies selection, not outcomes.

toolopen_docs

passCoverage vs. site type

weight 7

The tool set covers the whole core docs flow: search or browse the catalog, read a page or article, navigate the documentation tree.

Tool quality

96 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 429ms of navigation.

toolask_pixeltable

passCanonical entry point

weight 3

All 5 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 5 declared input schemas are structurally valid object schemas.

passSchema quality

weight 4

All 4 of 5 tool schemas that declare parameters describe them (the other 1 declares 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: 2 names do not start with a verb (open_docs).

toolopen_docs

fix

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

passStub detection

weight 4

All 5 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

1 of 5 tool descriptions leave an agent guessing: copy_install_command Omits what changes when it runs, and what comes back.

toolcopy_install_command

copy_install_command: weak

Trust

0 / 100 · weight 20

failAnnotations present

weight 5

2 of 2 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.)

toolask_pixeltable

ask_pixeltable, search_blog

fix

{
  name: "ask_pixeltable",
  // 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 }
}

not applicableAnnotation mismatch

weight 5

No tool declares a readOnlyHint, so there is no safety claim to contradict.

not applicableUntrusted content hint

weight 3

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

not applicableHint vs. observed

weight 4

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.

warningInjection surface

weight 3

1 of 5 tools carry instruction-shaped text in their own metadata: navigate_pixeltable Description instructs agent on tool usage and preference..

toolnavigate_pixeltable

navigate_pixeltable: Description instructs agent on tool usage and preference.

fix

{
  name: "navigate_pixeltable",
  // 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

Find the page that explains authentication.missed

choseopen_docsexpected docs searchkind mismatch

The tool the model chose does not look like the kind of tool this intent needs.

arguments

{
  "path": "/docs/authentication"
}

Read that page to me.missed

choseno toolexpected page readkind not applicable

No tool was picked for this intent.

arguments

{}

What other pages are in the same section?missed

choseno toolexpected navigationkind 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 151.0.7922.34)
chrome: 151.0.7922.34
capture shim: v3
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 5
invoked: not invoked; a live audit calls them
run time: 12s
finished: Sep 7, 2026

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