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

Better Design

NPM · BETTER-DESIGN · 2 COMPONENTS

A design harness for AI coding agents: design systems, design principles, icons and UI review.

+15 this week 72 Trust /100

Last scanned (1 hour ago)

Scores higher than 44% of npm servers

Category Design and Media

Trust breakdown (7 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 → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 32 of 99 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability36
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 24335 tokens (~553/item across 44 items; 42 tools + 2 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 Management74
  • Stability check failed: the tool surface changed between 0.37.0 and 0.51.0: 10 tool removals, 0 breaking changes, 14 additions. See how to fix → Fail
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 97% of tool parameters carry a description.Partial
  • Structured output schemas are declared (19% of tools); any adoption earns full credit.Pass
Tool Safety88
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get-inspiration" implies "send" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 44 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (17)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

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.

  • 16 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 −19
    • Malware scan: pass → unverified ▼ security
    • Stability: pass → fail ▼ security
    • Schema quality: 477 → 553 ▼ functional
    • Package version: 0.48.0 → 0.51.0 functional
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 −1
    • Stability: pass → 0.90 functional
  • 2 Nov 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 1 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 29 Oct 26 0
    • Stability: 0.97 → pass security
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 22 Nov 2026 · Analysed npm/better-design@0.51.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 99 packages
Packages resolved 99
Stale 32
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 42 exposed · ~23,862 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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
review-ui-code ~825

Deterministic UI and UX review of React component source and its CSS, and of SwiftUI .swift views. Run it on every UI file you write or change, including globals.css and a one-file .html page (its <style> blocks are checked), before you present the result. Pass the markup of every mock product screen or embedded panel too, not only the page around it. When CSS references a framework font variable, include the layout or font-loader .ts/.tsx/.js/.jsx module in the same call. get-review-rules gives you the judgment rules to apply yourself. This tool is the mechanical half: it parses the code and returns exact findings with line numbers and fixes, the same input always producing the same findings. It catches: - Native elements the installed design system already ships: raw <button>, <input>, <select>, <textarea>, <table>. - Raw <aside> app shells and repeated record rows that bypass installed Sidebar and Table compositions. - Undefined font variables that leave the rendered app on an unintended fallback family. - Hardcoded colors and Tailwind arbitrary color values that bypass semantic tokens, raw palette classes (bg-white, text-gray-500), and dark: forks. - Generated-UI tells: letter-spaced capital labels, a left-edge stripe on a callout, selected row or active nav item, gradient text, eyebrow labels above titles, em dashes in copy, a page title laid over a full-bleed product photo or video. - Signs of generated design, each with its fix: any use of Instrument Serif or IBM Plex (class, font-family, theme variable, next/font or @fontsource import), an Instrument Serif headline with negative tracking, italic emphasis in headlines or body copy, section numbers such as 01 or §, monospace file paths used as labels, many shades or opacities of one colour in one file, a bordered container inside a bordered container, and a divider between every item. - A website menu that opens as a side sheet or drawer instead of dropping down under the header. - Marketing pages on a phon…

NameTypeReqDescription
contextstring–Optional. One sentence on WHY you are calling this and what the user asked for (e.g. 'adding nav icons for the fintech dashboard'). Used for usage analytics, and to pick the next step a UI or UX prin…
filesarrayyesThe .tsx, .jsx, .ts, .js, .css, .html, .svg and .swift files to review, as written. Send an icon's own file beside the pages that use it, so a nudge finding can name the viewBox or path to fix.

No output schema declared.

No examples provided.

send-feedback ~174

Tell Better Design about a bug, a missing feature or wrong output you hit while using its tools or API. A person reads every report and approves any fix. Send one report per problem, once you have finished what the user asked. Say what you tried, what you expected and what came back. Leave out secrets, personal data and the user's private code. Sending a report never spends credit.

NameTypeReqDescription
actualstring–What you got back instead.
attemptedstring–What you tried to do, and the request you sent.
expectedstring–What you expected to get back.
kindstringyesWhat kind of problem this is.
summarystringyesOne sentence: what is wrong or missing.
surfacestringyesThe endpoint path or MCP tool name you called.

No output schema declared.

No examples provided.

set-design-config ~372

Write exact design-token values (colors, radius, fonts, icon library, layout density) onto a generated project. Use this when the user states concrete values ("make primary oklch(0.62 0.11 45)", "radius 12px"), or names a site whose theme to apply through `themePreset`. It merges over the current config and persists, so the change survives restarts and every later get-design-config returns it. Saved config is publicly readable by anyone with the fragment config URL. For vague direction ("warmer", "more playful"), iterate with the user toward concrete values first; do not invent numbers on their behalf.

NameTypeReqDescription
configobject–Partial design config to merge over the current one. Only pass the fields the user changed. Colors are oklch() strings (e.g. 'oklch(0.62 0.11 45)'); radius is a CSS length (e.g. '0.75rem'); fonts are…
contextstring–Optional. One sentence on WHY you are calling this and what the user asked for (e.g. 'adding nav icons for the fintech dashboard'). Used for usage analytics, and to pick the next step a UI or UX prin…
projectIdstringyesThe project id returned by create-design-system.
themePresetstring–Optional. The name of a site whose measured theme to apply, such as 'Railway'. It sets the colors, and the radius and font when the theme has them. Values in `config` win over the theme. A name with…

No output schema declared.

No examples provided.

set-team-rules ~464

Save the team rules you drafted with the person, so every agent on this account reads them and review checks work against them. Call get-team-rules first: with no rules saved it gives you the outline and the steps. With projectId it saves one piece of that client project instead: its guidelines (no screen or part), a use, never or pairing rule for one part or value (part and kind), a never rule for the whole brand (kind never, no part), or a spec on a screen or on one part of it (screen, plus part). Call this only after the person has read the whole draft and said to save it. Never save text the person has not seen. When different text is already saved, it refuses and replaces nothing: show the person both, and call again with replaceExisting: true only after they agree.

NameTypeReqDescription
contextstring–Optional. One sentence on WHY you are calling this and what the user asked for (e.g. 'adding nav icons for the fintech dashboard'). Used for usage analytics, and to pick the next step a UI or UX prin…
kindstring–With projectId: "guidelines", "use", "never", "pairing" or "spec". A screen alone means spec; nothing at all means guidelines; a part needs its kind.
markdownstringyesThe whole rules document in Markdown, in the outline get-team-rules gives, or one project piece. Up to 32 KB for team rules or project guidelines, 4 KB for a part rule or spec.
partstring–With projectId: the part or value the rule or spec is about, such as "Button" or "--primary".
personApprovedbooleanyesTrue only after the person read this exact draft and said to save it.
projectIdstring–Save into this client project instead of the account's team rules. The project must belong to this account.
replaceExistingboolean–True only after the person agreed to replace the rules already saved.
screenstring–With projectId: the screen a spec belongs to, such as "sign-up".

No output schema declared.

No examples provided.

use-device ~422

Look at and check an app on the user's own iPhone or iPad, with no simulator. Start with `list`: it shows each connected device and the setup step it still needs. Then take a `screenshot`, switch dark mode and text size with `settings`, `record` a demo, `install` a build made for a device, or `launch` an app and read what it prints. A screenshot works on any app on the phone, so it can also show a design the user likes. This server runs on the user's Mac and acts on the phone through Xcode's devicectl.

NameTypeReqDescription
actionstringyes`list` shows the connected iPhones and iPads and the setup step each one still needs. `screenshot` returns the screen as an image. `settings` switches dark mode and text size. `record` records the sc…
appPathstring–For `install`: the absolute path of an .app built for a device (the iphoneos SDK), signed with your team.
appearancestring–For `settings`: light or dark mode.
bundleIdstring–For `launch`: the app's bundle identifier.
contextstring–Optional. One sentence on WHY you are calling this and what the user asked for (e.g. 'adding nav icons for the fintech dashboard'). Used for usage analytics, and to pick the next step a UI or UX prin…
devicestring–The device's name or UDID, as `list` shows it. Leave it out when one device is connected.
secondsinteger–For `record`: how long to record. For `launch`: how long to read the app's output.
textSizestring–For `settings`: the text size. `large` is the default size.

No output schema declared.

No examples provided.

Install

How do I install the Better Design MCP server?

Better Design runs locally as an npm package, launched with npx -y better-design mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · better-design

# add to Claude Code
claude mcp add marvkr-better-design -- npx -y better-design mcp
Common questions

What is the Better Design MCP server?

Better Design is an MCP server listed in the public MCP registry as io.github.marvkr/better-design. A design harness for AI coding agents: design systems, design principles, icons and UI review. This page covers its npm package (better-design).

Is the Better Design MCP server safe to use?

Better Design scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Better Design MCP server expose?

Better Design exposes 42 tools: get-ui-principle, get-ux-principle, get-swiftui-guide, get-review-rules, plan-video, and 37 more. Their descriptions and schemas cost roughly 23,862 tokens of context every time the server is loaded.

Is the Better Design MCP server still maintained?

Better Design is still listed as active in the MCP registry. We last reached this channel on 22 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Better Design MCP server under?

Better Design declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Better Design MCP server?

VerifyMCP ran 17 checks on Better Design, covering Malware scan, Known CVEs, Install scripts, Dependency health and 13 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.