Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.mishaovcharenko/uiscanner

NPM · UISCANNER-MCP · SCANNED AUG 3

Design tokens + a build prompt from any URL, right inside Claude Code, Cursor, and Codex.

Available components

+16 this week 62 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 33 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 807 tokens (~134/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · uiscanner-mcp

# add to Claude Code
claude mcp add mishaovcharenko-uiscanner -- npx -y uiscanner-mcp
# add to Codex CLI
codex mcp add mishaovcharenko-uiscanner -- npx -y uiscanner-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mishaovcharenko-uiscanner": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "uiscanner-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add mishaovcharenko-uiscanner --command npx --arg -y --arg uiscanner-mcp
# ~/.hermes/config.yaml
mcp_servers:
  mishaovcharenko-uiscanner:
    command: "npx"
    args: ["-y", "uiscanner-mcp"]
// mcp.json
{
  "mcpServers": {
    "mishaovcharenko-uiscanner": {
      "command": "npx",
      "args": [
        "-y",
        "uiscanner-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Aug 26 +62
    • Provenance: unverified → fail security
    • Known CVEs: unverified → partial security
    • Install scripts: unverified → pass security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • MCP protocol: unverified → pass functional
    • Maintenance: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Schema quality: unverified → 100 functional
    • License: unverified → pass functional
    • Tool coverage: unverified → 100 functional
    • Schema quality: unverified → excellent functional
    • Licence: MIT functional
  • 1 Aug 26 −37
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 +18
    • Provenance: unverified → fail security
    • Malware scan: pass → unverified security
    • Install scripts: unverified → pass security
    • Dependency health: partial → unverified functional
    • Maintenance: unverified → pass functional
    • Schema quality: unverified → 100 functional
    • License: unverified → pass functional
    • Tool coverage: unverified → 100 functional
    • Licence: MIT functional
  • 29 Jul 26 −27
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Dependency health: unverified → partial functional
  • 27 Jul 26 46

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 5 exposed · ~493 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
get_teardown ~92

Fetch a finished teardown by its id or its uiscanner.com/t/<id> link. Returns the same tokens, sections, brand, and build prompt as ui_teardown, without re-scanning.

NameTypeReqDescription
idstringyesA teardown id, or a uiscanner.com/t/<id> link.
include_screenshotbooleanAlso return the rendered page as an image. Default false.
NameTypeReqDescription
anti_slop
brand
completeness
created_atstring|null
design_mdstring|null
dimensions
domainstring
freshness
full_screenshot_urlstring|null
idstring
promptstring|null
scorenumber|null
score_bandstring|null
sections
source_urlstring
targetstring
tokens
urlstring

No examples provided.

retarget_teardown ~90

Re-tailor a finished teardown's build prompt to a different archetype WITHOUT re-scanning (cheaper and faster than a new scan). Pass the teardown id or its link and the new target.

NameTypeReqDescription
idstringyesA teardown id, or a uiscanner.com/t/<id> link.
targetstringyesThe archetype to re-tailor the build prompt for.
NameTypeReqDescription
anti_slop
brand
completeness
created_atstring|null
design_mdstring|null
dimensions
domainstring
freshness
full_screenshot_urlstring|null
idstring
promptstring|null
scorenumber|null
score_bandstring|null
sections
source_urlstring
targetstring
tokens
urlstring

No examples provided.

ui_probe ~87

Cheap pre-flight before a scan: is a URL syntactically valid and public (not localhost / a private or blocked target), and is there a recent cached teardown to reuse? Spends no scan. Call it before ui_teardown to avoid wasting a scan on an unscannable URL.

NameTypeReqDescription
urlstringyesPublic URL to check, e.g. https://stripe.com
NameTypeReqDescription
cached
reasonstring|null
scannableboolean
urlstring

No examples provided.

ui_teardown ~186

Scan any public website and get a design teardown: design tokens (colors, fonts, type scale, radii, spacing, shadows, motion), section structure, and a Claude-tailored build prompt to recreate the look. Describes and tokenizes, never copies asset bytes. Returns an id and a shareable uiscanner.com/t/<id> link. Takes up to ~3 minutes. Each scan spends one unit of your plan quota; prefer retarget_teardown over a second scan, and ui_probe first to avoid spending a scan on a blocked URL.

NameTypeReqDescription
include_screenshotbooleanAlso return the rendered page as an image. Larger payload; default false.
targetstringWhat you're building, to tailor the prompt. Default: general.
urlstringyesPublic URL of the page to scan, e.g. https://stripe.com
NameTypeReqDescription
anti_slop
brand
completeness
created_atstring|null
design_mdstring|null
dimensions
domainstring
freshness
full_screenshot_urlstring|null
idstring
promptstring|null
scorenumber|null
score_bandstring|null
sections
source_urlstring
targetstring
tokens
urlstring

No examples provided.

whoami ~38

Show the signed-in plan and scans remaining in the current window. Read-only; spends no scan. Worth calling before a batch of teardowns.

Input schema present but exposes no named parameters.

NameTypeReqDescription
authenticatedboolean
creditsnumber
planstring
quota

No examples provided.