UI design MCP: design references, intent routing, anti-slop static detector and gate. No API key.
PyModel Designer Skill MCP (UI design MCP)
The io.github.PyModel/designer-skill-mcp server is a UI design MCP that provides design references, intent routing, and an anti-slop static detector and gate. The server is described as requiring no API key.
π οΈ Key Features
Design references
Intent routing
Anti-slop static detector and gate
No API key
π Use Cases
Routing UI-related intents for design workflows
Using design references during UI design
Detecting and gating undesirable βslopβ via static detection
β‘ Developer Benefits
Avoids API-key setup
β οΈ Limitations
Available description does not specify supported tools, interfaces, or authentication beyond βNo API key.β
Paste into your agent (Claude Code, Codex, Cursor, any MCP client). It installs the skill, wires the MCP and verifies the tools:
text
Add designer-skill. The designer core is keyless: it routes requests, loads guidance, checks contrast, converts design tokens and runs static and rendered checks. The Niblet catalogue is built in and optional: with a NIBLET_TOKEN it supplies real screens and licensed materials; without one those tools answer guidance and everything else works.
1. Install or refresh the skill into the user skill directory (not this project):
npx skills add PyModel/designer-skill --skill designer-skill -g -y
2. Add the local MCP using this client's native MCP configuration, in the user-level (not project-level) config:
Name: designer-skill
Transport: stdio
Command: npx
Args: -y @pymodel/designer-skill-mcp@latest
No API key is needed. Add NIBLET_TOKEN only if the user already has a Niblet key and asks for catalogue references.
3. Verify: list the designer-skill server's tools and confirm get_preflight_brief, dispatch_intent, review_and_gate are present. Do not run a sample check.
When setup is complete, confirm the skill is installed and the three named tools are exposed. On UI work: call get_preflight_brief, use dispatch_intent and load only relevant guidance. If an unresolved visual question warrants retrieval, use the catalogue tools (they answer guidance when no key is set; continue without them). Run review_and_gate as supplemental static evidence, then perform the required rendered, functional and accessibility checks in the host. Never treat static success as UI PASS. Preserve audit/plan scope. Continue an active authorized task; otherwise report designer-skill ready, and report Niblet paired only if its tools were actually observed.
No Niblet key? Continue from local product evidence; catalogue retrieval is optional. To get more references, see More references with Niblet.
Or pick one:
Install
π£ Claude Code plugin (skill + MCP)
/plugin marketplace add PyModel/designer-skill then /plugin install designer-skill@pymodel
π’ Codex plugin
codex plugin marketplace add PyModel/designer-skill, then install designer-skill from pymodel in /plugins
β« Cursor plugin
Install from the marketplace; ships mcp.json, skills, /designer-setup Β· /designer-status
π΅ MCP only, any client
claude mcp add -s user designer-skill -- npx -y @pymodel/designer-skill-mcp (same args for codex mcp add, pythinker mcp add --transport stdio)
π Skill only
npx skills add PyModel/designer-skill --skill designer-skill or copy skills/designer-skill/ into ~/.claude/skills/ / ~/.codex/skills/
Standalone MCP config (the plugin's own mcp.json pins the release it was tested with instead of @latest):
flowchart LR
A[Prompt] --> B[get_preflight_brief]
B --> C[dispatch_intent]
C --> D[get_reference]
D --> E[Build / polish UI]
E --> F[review_and_gate]
F -->|FAIL: fix| E
F -->|static checks pass| G[Rendered checks<br/>by the host]
classDef start fill:#f8fafc,stroke:#94a3b8,color:#18181b
classDef route fill:#eff6ff,stroke:#3b82f6,color:#1e3a8a
classDef know fill:#faf5ff,stroke:#7c3aed,color:#4c1d95
classDef work fill:#fff7ed,stroke:#e87a3d,color:#7c2d12
classDef gate fill:#ecfdf5,stroke:#10b981,color:#065f46
classDef host fill:#fff1f2,stroke:#e11d48,color:#881337
class A start
class B,C route
class D know
class E work
class F gate
class G host
π΅ Route
π£ Know
π’ Check
dispatch_intent maps "make it pop" or "it feels off" to design verbs and topic references, recommends at most four and names every other match.
A 44-rule deterministic detector backs review_and_gate, which reports each required rule as ran, unsupported, unresolved or waived.
The gate is static only, by design: overall status is FAIL or NOT_VERIFIED, never a rendered-readiness pass. verify_rendered loads a local page in a real browser (the project's own Playwright and axe-core) and reports page load, console errors, broken images, clipped text, overflow and accessibility with screenshots; without Playwright it reports NOT_RUN. check_contrast measures explicit color pairs.
More references with Niblet (optional)
Everything above works with no account and no key. For real product screens to compare against, recorded design references, license-recorded fonts and icons, and React component source:
The four catalogue tools (find_ui_references, get_design_reference, find_ui_materials, get_ui_component) then answer from the hosted Niblet MCP; you do not install a second server. Keep the key in the client's secret store, never in a commit or a prompt.
Without a key, with NIBLET_DISABLED=1, or when the catalogue is unreachable, those tools answer a short guidance text and every other tool keeps working: a transient failure is retried three times, then the catalogue is skipped for 60 seconds so no call waits on it. Catalogue trouble is never a tool error.
Niblet ecosystem
Owner
Responsibility
designer-skill
One entry point for scope, routing, craft/UX guidance and verification reporting
Niblet platform
Real-screen catalogue, recorded design references and license-recorded materials
Niblet MCP (hosted)
Serves the four catalogue tools this server passes through, including get_ui_component React source
Agent host
Authorized file/dependency changes, browser/native interaction, rendered inspection and evidence
designer-skill is an MCP client of the hosted Niblet MCP and passes its four tools through under the same names, images included. If a Niblet server is also connected directly, use one of the two for a question, never both, and do not infer connectivity from installation. Consult niblet-catalogue for deployment differences, bounds and licensing.
Use one product-grounded design contract. Niblet's surface modes (Persuade, Operate, Read, Experience) describe the user's job; designer-skill's execution modes (audit, plan, refine, implement, system) describe permitted work. They are independent: an Operate surface can receive a read-only audit or an authorized refinement. Existing product tokens, components and real content win over reference aesthetics. Component retrieval does not authorize dependency installation or source writes, and neither MCP certifies rendered quality.
Example:"Use designer-skill to redesign this pricing page without breaking functionality." β get_preflight_brief β dispatch_intent β get_reference β edit β review_and_gate.
Scope-adaptive implementation and evidence workflow
π΄ extended
live-mode
Authorized source variants using host-discovered preview tools
π΄ extended
css-techniques
Modern CSS: container queries, :has(), clamp(), logical props
π΄ extended
motion-vocabulary
Map a feel word ("the bouncy thing") to the standard motion term
π΄ extended
fluid-input-principles
Gesture-first fluid-interface principles translated for web
π΄ extended
native-web
Platform-correct mobile web: tap, viewport, safe areas, zoom
π΄ extended
worst-case-data
Design and verify against extreme real data, not demo values
π΄ extended
variant-prototyping
Time-boxed side-by-side variants for genuinely open decisions
π΄ extended
dependency-selection
Method for choosing or adding a UI dependency, not a picks list
π΄ extended
niblet-catalogue
Optional real-screen references and materials via Niblet; advisory, unconfigured-safe
π΄ extended
craft-provenance
Historical capability mapping and attribution; load only when needed
π΄ extended
native-platforms
iOS, Android and desktop native UI: system components, text scaling, device checks
π΄ extended
Plus 26 ux/* references, authored in skills/ux-designer/ and vendored at skills/designer-skill/reference/ux/ (generated by node scripts/sync-ux.mjs, checked by test), so a designer-skill-only install is self-contained. Each SKILL.md is a short router with a one-line description; references load only when a task needs them.
Compact scope and verification contract; call first
load_project_context
Read PRODUCT.md and DESIGN.md and detect design tooling (tokens, shadcn, Storybook, Tailwind, Playwright); requires cwd
get_skill_contract
This skill's full SKILL.md contract and reference routing map (not the project's design system)
get_reference
Load one named reference (designer or ux/*) on demand
list_commands
Discover canonical commands and aliases
get_command
Command help and reference names, not eagerly loaded documents
dispatch_intent
Route a request to commands and topic references; names every match, recommends at most four reads
validate_design_direction
Validate inspected contextSources and preservation/new-direction inputs; stores nothing
get_palette_seed
Optional seed for an authorized new palette
check_contrast
WCAG 2.2 contrast for explicit color pairs, with large-text thresholds and advisory APCA Lc
convert_design_tokens
W3C Design Tokens (DTCG) JSON to CSS custom properties or a Tailwind v4 @theme block
detect_antipatterns
Bounded static scan: coverage, per-file engine and gaps, file hashes; requires cwd and target
review_and_gate
Static verification per required rule; never an overall PASS by design; requires cwd and target
verify_rendered
Load a local page in a real browser: load, console errors, broken images, clipped text, overflow, axe-core, screenshots. Uses the project's Playwright; NOT_RUN without it
find_ui_references
Optional Niblet catalogue: real product screens for one design question (needs NIBLET_TOKEN); untrusted results
get_design_reference
Optional Niblet catalogue: recorded colors, typography and components for a web screen or pack
find_ui_materials
Optional Niblet catalogue: license-recorded fonts, icons, animated icons and components
get_ui_component
Optional Niblet catalogue: a component's shadcn registry item; authorizes no install or write
cd designer-skill-mcp
npm ci
npm run build # syncs skills/ β assets/ (generated, gitignored), compiles TypeScript
node --test checks/core.mjs # contract checks against the built dist
npm run typecheck && npm test# tsc over src + test, then vitest; `npm run smoke` drives the packed tarball
Skill robustness checks
Edit UX guidance only in skills/ux-designer/references/; npm run sync-skill regenerates the standalone mirror before bundling. Run node scripts/sync-ux.mjs from the repository root for filesystem-only distribution.
Run reports now use v2, plus a host-owned verification plan. Validate both bundled JSON schemas, then run the dependency-free skills/designer-skill/scripts/validate-report.mjs REPORT PLAN AUTHORIZED_ROOT for evidence hashes, confinement, revision/plan matching and rendered-readiness semantics. Its own PASS means report validation, not UI certification. Legacy v1 reports fail closed and must be regenerated from real evidence; update host readers/writers together.
Behavioral action-plan cases and a deterministic grader live in evals/designer-skill/. Synthetic grader tests do not count as model evaluations, and model proposals do not prove actual tool-use compliance or rendered quality. Keep model, host, skill hash and repetitions with evaluation results.
Every HTTP bind requires at least one --root. Every bind validates the Host header and refuses a browser Origin that is not an accepted host; a non-loopback bind also requires DESIGNER_SKILL_HTTP_TOKEN (Authorization: Bearer β¦) and at least one --allowed-host.
Release:./scripts/release.sh "notes" bumps and syncs every version, verifies, tags and pushes; publish.yml publishes npm (with provenance), the MCP registry entry and the GitHub release. Contract details: docs/HARDENING.md.