seopress.org WebMCP audit

Name: seopress.org WebMCP audit
Creator: ora

Rescan

audited Nov 10, 2026in 16s

72/ 100100% of the applicable check weight evaluated

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

Shared experience87

Tool selection100

Tool quality83

Trust0

https://seopress.org

Tools

0 read, 0 write, 2 undeclared

Loading map

search_site

Full-text search of SEOPress.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://www.seopress.org/

implementation

viaimperative

entry pointprovideContext

registered after491ms

executepresent

api surface

queryrequired

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

3 findings

failCanonical entry point

weight 3

Every tool uses the removed provideContext API; register each tool with document.modelContext.registerTool().

fix

// document.modelContext is the canonical entry point - the navigator.modelContext alias is deprecated.
document.modelContext.registerTool({ /* ... */ });

failAnnotations present

weight 4

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.)

search_site, fetch_as_markdown

fix

{
  name: "search_site",
  // 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 }
}

warningDescription quality

weight 5

1 of 2 tool descriptions leave an agent guessing: search_site Does not say what comes back from the search..

search_site: weak

fix

{
  name: "search_site",
  description: "Describe what this tool does, when to use it, and what it returns."
}

tool json

{
  "name": "search_site",
  "description": "Full-text search of SEOPress.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "description": "The search query."
      }
    },
    "required": [
      "query"
    ]
  },
  "annotations": {}
}

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: obstruction A cookie consent banner partially covers the main content of the page..

obstruction: 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 2 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

83 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 491ms of navigation.

toolfetch_as_markdown

failCanonical entry point

weight 3

Every tool uses the removed provideContext API; register each tool with document.modelContext.registerTool().

toolsearch_site

fix

// document.modelContext is the canonical entry point - the navigator.modelContext alias is deprecated.
document.modelContext.registerTool({ /* ... */ });

passSchema validity

weight 4

All 2 declared input schemas are structurally valid object schemas.

passSchema quality

weight 4

All 2 tool schemas describe their parameters, and every description stays within Chrome's size guidance.

passNaming quality

weight 2

All 2 tool names are consistent, verb-led, and within Chrome's size guidance.

passStub detection

weight 4

All 2 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

warningDescription quality

weight 5

1 of 2 tool descriptions leave an agent guessing: search_site Does not say what comes back from the search..

toolsearch_site

search_site: weak

fix

{
  name: "search_site",
  description: "Describe what this tool does, when to use it, and what it returns."
}

Trust

0 / 100 · weight 20

failAnnotations present

weight 4

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.)

toolsearch_site

search_site, fetch_as_markdown

fix

{
  name: "search_site",
  // 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 4

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 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 2 intents

I want to search site on this site.ok

chosesearch_siteexpected search sitekind matched

arguments

{
  "query": "site"
}

I want to fetch as markdown on this site.ok

chosefetch_as_markdownexpected fetch as markdownkind matched

arguments

{
  "url": "https://www.seopress.org/"
}

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: 2026-11-10
mode: fast
pages: 1 - entry page only
tools: 2
invoked: not invoked; a live audit calls them
run time: 16s
finished: Nov 10, 2026

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