ux-mcp

ux-mcp is a command for Claude Code from Laith0003/ux-skill. It costs 72 tokens per session (1,978 once invoked), scanned A, original, MIT.

A local server that makes the ux-skill design engine available to any client supporting MCP, a standard way for AI tools to call external capabilities. It exposes design recommendations, checks, saved guidance, and design reference data.

In plain words
What is it for?
Use it to request interface design recommendations, check designs against rules, share design constraints across agents, or call the engine from continuous-integration tools.
Why use it?
It lets tools such as Cursor, Windsurf, or Claude Desktop use the same design guidance without installing the complete plugin.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the ux plugin — 25 commands, 5 agents shipped together

Good fit Use it to request interface design recommendations, check designs against rules, share design constraints across agents, or call the engine from continuous-integration tools.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/laith0003/ux-skill/ux-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Laith0003/ux-skill

Made for: Claude Code.

Or install ux, the plugin that ships this one along with the rest of its 25 commands, 5 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ux-mcp

README.md
[![agentmods](https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-mcp.svg)](https://agentmods.dev/commands/laith0003/ux-skill/ux-mcp)
Your own site
<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-mcp"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,978 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01978
Opus 5 $0.00036 $0.00989
Sonnet 5 $0.00014 $0.00396
Haiku 4.5 $0.00007 $0.00198

Measured 8d ago against content hash 3d2529535c5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ux-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/ux-mcp.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ux-mcp — the design intelligence MCP

One server. Fourteen tools. Every MCP-aware client gets the engine.

This is the asymmetric move. None of the leading Claude UX skills (ui-ux-pro-max-skill, open-design, taste-skill, huashu-design, stitch, nothing-design, hallmark, material-3) ship an MCP server. Doing so turns ux-skill into the canonical design-intelligence MCP — agents in any host can call into the same recommender, linter, and manifests that the plugin uses, without needing to install the plugin itself.

When to use

  • You're using Cursor, Windsurf, Claude Desktop, or any other MCP-capable host and want ux-skill available without forcing the host to learn the plugin layout.
  • You're orchestrating a multi-agent pipeline and need a single source of truth for design constraints across agents.
  • You're writing CI tooling that calls the recommender or linter from a long-running daemon rather than spawning a CLI each time.

When to skip

  • You're already inside Claude Code with the plugin installed — the slash commands hit the engine directly, no MCP transport needed.
  • You only need a one-shot recommendation or lint — ux recommend / ux lint from the CLI is simpler.

Install

The MCP transport is an optional dependency to keep the base install slim:

pip install 'uxskill[mcp]'

Or, if you already have uxskill:

pip install 'mcp>=1.0'

Start the server

ux-mcp                       # entry point (preferred — wired by pyproject.toml)
python3 -m engine.mcp.server # equivalent module form

The server speaks stdio JSON-RPC. Logs go to stderr only; stdout is reserved for the protocol stream.

Exposed tools (14)

Tool What it does
ux_recommend Run the 5-parallel-search recommender over a brief. Returns style + palette + type pair + motion + components + brand exemplars + guardrails + rationale.
ux_lint Run the anti-AI-slop regex linter over paths. Returns findings with rule id, severity, file, line, excerpt, fix.
ux_styles Return all 84+ entries from data/styles.json.
ux_palettes Return all 176+ entries from data/palettes.json. Optional mode filter (light / dark).
ux_type_pairs Return all 70+ entries from data/type-pairs.json.
ux_components Return all 148+ entries from data/components.json. Optional category filter.
ux_industries Return all 184+ entries from data/industries.json. Optional category filter.
ux_motion_presets Return all 57+ entries from data/motion-presets.json. Optional category filter.
ux_anti_patterns Return all 35+ regex rules from data/anti-patterns.json. Optional severity filter.
ux_brands Return all 92 brand specs from data/brands/*.json (Apple, Stripe, Linear, Tesla, Notion, etc.). Optional category filter.
ux_landing_patterns Return all 24+ entries from data/landing-patterns.json. Optional category filter.
ux_persist_save Persist a recommendation as .ux/design-system/MASTER.md in a given project root. Idempotent — same input writes byte-identical bytes.
ux_persist_load Load .ux/design-system/MASTER.md back into a structured dict.
ux_stats Return the engine version and per-manifest entry counts. Useful as a health probe.

Read the full file on GitHub · 208 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 208 lines · 72 tokens per session scan A 3d2529535c5c

Subscribe to this mod's changes

ux-mcp is a command published in the GitHub repository Laith0003/ux-skill (68 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 1,978 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other commands, from other repositories

accessibility-audit

You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits, identify barriers, provide remediation guidance, and ensure digital products are accessible to all users.

wshobson/agents · 0 tokens

cinematic-scroll

Build cinematic, scroll-driven websites with the cinematic-scroll skill — pinned chapter reveals, hero/multi-depth parallax, scroll-linked 3D tilt and camera moves, and environment-morphing backgrounds. From a single self-contained .html scroll section (Mode A) to a full Next.js release site with optional AI-generated…

MustBeSimo/cinematic-scroll-skill · 0 tokens

healthcare-ux-specialist

Use when designing clinical or patient-facing interfaces. Clinical workflows, displaying sensitive patient data, HIPAA considerations in the UI, and medical terminology patients do not speak.

imsaif/design-with-claude · 32 tokens

motion-designer

Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.

imsaif/design-with-claude · 37 tokens

spacing-layout-specialist

Use when spacing looks arbitrary. Padding and margins off any scale, inconsistent gaps between the same components, no grid underneath, or a layout that needs a denser mode.

imsaif/design-with-claude · 34 tokens

add-library

Kullanıcı "kütüphane ekle", "library ekle", "tasarım sistemi ekle", "design system ekle" dediğinde bu komutu uygula.

atezer/FMCP · 0 tokens