unsolved.how WebMCP audit

audited Nov 17, 2026in 10s
96/ 100100% of the applicable check weight evaluated

3 tools registered. Strongest in tool selection, weakest in shared experience.

Shared experience87
Tool selection100
Tool quality100
Trust100
https://unsolved.how
Captured view of https://unsolved.how

Tools

3 read, 0 write
Loading map
search_problems: pass

search_problems

Find problems in the UNSOLVED registry of open problems in AI by words, field or status. It takes keywords or a question in plain words and returns the problems that have them, best match first: those with every word, then those with only some. If no word matches, it returns the whole registry to choose from by meaning; the answer’s match says which happened. With no arguments it lists the whole registry in number order. Read one in full with get_problem.Answers a question. Declared read only.
pagehttps://unsolved.how/
implementation
viaimperative
entry pointdocument
registered after289ms
executepresent
api surface
queryoptional
fieldoptional
statusoptional
annotations
read onlytrue
untrusted contentnot declared
titleSearch the registry
0 findingsNo check named this tool.
tool json
{
  "name": "search_problems",
  "description": "Find problems in the UNSOLVED registry of open problems in AI by words, field or status. It takes keywords or a question in plain words and returns the problems that have them, best match first: those with every word, then those with only some. If no word matches, it returns the whole registry to choose from by meaning; the answer’s match says which happened. With no arguments it lists the whole registry in number order. Read one in full with get_problem.",
  "inputSchema": {
    "properties": {
      "query": {
        "description": "Keywords or a question in plain words, such as \"prompt injection\" or \"is AI taking entry-level jobs?\". Leave it out to list every problem.",
        "maxLength": 200,
        "type": "string"
      },
      "field": {
        "description": "Only problems in this field, by name or slug, such as \"Climate & energy\" or \"climate-energy\".",
        "maxLength": 100,
        "type": "string"
      },
      "status": {
        "description": "Only problems with this status: open, progress (in progress) or solved.",
        "enum": [
          "open",
          "progress",
          "solved"
        ],
        "type": "string"
      }
    },
    "type": "object"
  },
  "annotations": {
    "readOnlyHint": true
  }
}
Showing search_problems

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 banner is present at the bottom 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
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.
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

100 / 100 · weight 25
passRegistration timing
weight 1
Every measured tool registered within 290ms of navigation.
toollist_developments
passCanonical entry point
weight 3
All 3 tools register on the canonical document.modelContext entry point.
passSchema validity
weight 4
All 3 declared input schemas are structurally valid object schemas.
passSchema quality
weight 4
All 3 tool schemas describe their parameters, and every description stays within Chrome's size guidance.
passNaming quality
weight 2
All 3 tool names are consistent, verb-led, and within Chrome's size guidance.
passStub detection
weight 4
All 3 tools declare an execute handler.
passRegistration errors
weight 2
No tool registration threw during the capture.
passDescription quality
weight 5
All 3 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

100 / 100 · weight 20
passAnnotations present
weight 4
All 3 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 4
No tool claims to be read-only while its own name or description says it writes (3 declared hints checked).
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 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.
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 search problems on this site.ok
chosesearch_problemsexpected search problemskind matched
arguments
{}
I want to get problem on this site.ok
choseget_problemexpected get problemkind matched
arguments
{
  "number": 0
}
I want to list developments on this site.ok
choselist_developmentsexpected list developmentskind 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.
Reads the site's public pages; takes a few seconds.
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
3
invoked
not invoked; a live audit calls them
run time
10s
finished
Nov 17, 2026
Checked the way in-browser agents discover tools: the top-level document's modelContext registry, read after the page settles.