web-stylebook-mcp
This server provides read-only, deterministic design guidance for coding agents.
Recommend scored design directions from product context, tone, audience, constraints, density, trust sensitivity, and other inputs, including rejected styles, pairings, assumptions, and confidence.
Compare 2–4 design directions across product fit, repeated-use suitability, density, trust, distinctiveness, accessibility risk, motion, and maintenance, returning favorable conditions and failure modes rather than a single winner.
Select relevant visual design principles by phase, surface, concerns, or explicit IDs, with placement guidance, application steps, verification checks, cautions, related principles, and relevance scores.
Select relevant UX principles by outcomes, surface, phase, or explicit IDs, with design questions, application steps, verification checks, cautions, references, and relevance scores.
Plan UI states for surfaces such as data tables, forms, checkout, chat, and developer consoles, including required/recommended/domain-specific states, triggers, must-show/must-not guidance, accessibility and motion guidance, and implementation order.
Compose role-based design tokens for color, typography, spacing, radius, motion, and density in JSON, CSS variables, Tailwind, or TypeScript, with light/dark modes, accent overrides, and WCAG contrast warnings.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@web-stylebook-mcp Recommend a design direction for a finance dashboard."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
web-stylebook-mcp
Design judgment for coding agents. It improves the UI you already have and shows the evidence.
English · 한국어

Left: a fixture dashboard written in a common generated style. Right: the same page after one
pass of the web-stylebook-design skill, run by Claude Opus 5.5 with no human edits. Fictional
data. How it was made, what was measured, and what it does not show →
It knows design. It bundles 24 researched foundations with 30 attributed sources, 25 interface principles, 23 UX principles, 48 visual directions and 520 real-world references. Each rule says when it applies, when it does not, and how to check the result.
It makes the agent finish the job. The agent captures the page, plans, edits the real source, captures again and compares. The run counts as
completeonly with matched before/after captures, kept links and test hooks, and behavior and accessibility checks. Otherwise the result isneeds-work, with a list of what is missing.It stays local. No API key, no model calls, no network, and it never reads your files. The same input always gives the same output.
Install
For any agent with skills (Claude Code, Codex, Cursor and others):
npx skills add seungdori/web-stylebook-mcpFor Claude Code, the plugin installs the skill and the MCP server together (Claude Code 2.1.275 or later):
/plugin install web-stylebook --marketplace seungdori/web-stylebook-mcpFor the MCP server only:
claude mcp add web-stylebook -- npx -y web-stylebook-mcp@latestcodex mcp add web-stylebook -- npx -y web-stylebook-mcp@latestCursor, Windsurf and Claude Desktop settings are in the reference.
Node 20 or later is required; npx skills needs Node 22.20 or later.
Related MCP server: WordPress Design System MCP Server
Use
Ask for a change to a screen you already have:
Improve the dashboard so on-call sees what is broken first.
The agent captures the page and calls get_design_improvement_plan. Then it edits your code,
checks what the edit kept with compare_page_revisions, and finishes with
validate_design_improvement_result. You get before/after screenshots, each change with its
reason, the checks that ran, and what was not verified.
For a new page, describe the product instead, for example "a landing page for a payments API".
The agent starts with recommend_design_direction and shows the candidates it ranked, plus the ones
it rejected and why.
If you ask for a review only, the agent audits and reports without editing anything.
Without MCP
The skill works without the MCP server. It runs the same tools from the shell and gets the same results:
npx -y web-stylebook-mcp toolsnpx -y web-stylebook-mcp call get_design_improvement_plan --input plan-args.jsonTools
For | Tools |
Improving an existing UI |
|
Reviewing |
|
Choosing a direction |
|
Principles and states |
|
Building |
|
The reference has an example for each tool, the result contracts, the resources and prompts, and the CLI.
More
Reference: tool examples, contracts, CLI and compatibility
Demo: the before/after above, with every evidence file
With/without showcase: ten paired builds, blind comparisons and recorded results
License
MIT. It covers the code and the bundled catalog snapshot. The webstylebook.com website itself is CC BY-NC; attribution details are in the reference.
Available Tools
6 toolscompare_design_directionsCompare design directionsARead-onlyIdempotent
Compare 2-4 directions across product fit, repeated-use suitability, density, trust, distinctiveness, accessibility risk, motion and maintenance. Returns each direction's favorable conditions and likely failure mode — never a single winner.
Inputs: directions (required), locale, product.
compose_design_tokensCompose design tokensARead-onlyIdempotent
Compile a starting set of role-based design tokens (color, typography, spacing, radius, motion, density) for a style in json / css-variables / tailwind / typescript, with light/dark/both modes, accent override, and WCAG contrast warnings.
Inputs: format (required), primaryStyleId (required), locale, density, +3 more.
get_design_principle_planPlan relevant design principlesARead-onlyIdempotent
Select a small set of practical visual-design principles for intent and iteration, semantic hierarchy, adaptive layout and density, typography and localization, tokens and themes, accessible interaction, and complete states and recovery. Filter by design concerns, surface, phase, or explicit ids. Returns placement guidance, application steps, verification checks, cautions, related principles, and deterministic relevance scores.
Inputs: limit, phase, locale, surface, +2 more.
get_ui_state_planPlan UI states for a surfaceARead-onlyIdempotent
For a surface (data-table, form, checkout, chat, developer-console), return required / recommended / domain-specific states with triggers, must-show, must-not, accessibility and motion guidance, plus an implementation order. Covers the non-happy-path.
Inputs: surfaceId (required), locale, styleId, criticalOnly, +3 more.
get_ux_principle_planPlan relevant UX principlesARead-onlyIdempotent
Select a small, evidence-labeled set of UX principles for a target outcome, surface, design phase, or explicit principle ids. Returns design questions, application steps, verification checks, cautions, references, and relevance scores. Treat the result as decision prompts rather than universal laws.
Inputs: limit, phase, locale, surface, +2 more.
recommend_design_directionRecommend a design directionARead-onlyIdempotent
Given product context, return scored style candidates with reason codes, rejected styles with reasons, secondary pairings, assumptions and confidence. Evidence-provider: the host model makes the final pick. Call before writing UI. The "tone" field (named "tone", not "tones") is an ARRAY of zero or more of: calm, technical, trustworthy, premium, editorial, playful, bold, experimental. Each candidate.score already includes soft penalties (density/motion/tone fit) that are not itemized in scoreBreakdown.
Inputs: productDescription (required), tone, avoid, locale, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct aspect of design guidance: direction recommendation, direction comparison, design principles, UX principles, UI state planning, and token composition. No two tools overlap in purpose.
All tool names follow a verb_noun pattern (recommend, compare, get, compose) with consistent use of snake_case and predictable object naming (e.g., get_design_principle_plan, get_ux_principle_plan).
6 tools is well-scoped for a design guidance server. Each tool covers a necessary function without redundancy or excessive specialization.
The set covers core design activities: direction selection, comparison, principles (design/UX), state planning, and token generation. A minor gap is the lack of a tool to apply or test tokens on actual components, but the scope is reasonable.
Maintenance
Related MCP Connectors
Give your agent a real design system: tokens, measured WCAG contrast, and rules to follow.
Read-only canon of design and copy rules for AI agents to audit generated UI, served as resources.
Give AI agents your deeepSpace design system: components, tokens, styles and code mappings.
Design systems your AI agent builds with and you reshape, plus standalone React components.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides AI assistants with access to a production-ready design system including Tailwind CSS component patterns, style guides (colors, typography, spacing), and Web Components specifications for consistent UI development.-
- AlicenseNot gradedqualityDmaintenanceProvides AI agents with component documentation, usage examples, and design tokens from the WordPress Design System, enabling them to follow the latest design system guidance for creating user interfaces.GPL 2.0
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to query a workspace's design system before writing UI and validate generated code against the same system afterward, using configurable token and component sources.13 npm1MIT
- AlicenseNot gradedqualityBmaintenanceProvides a real API for coding agents to look up design system components, props, and tokens, preventing guessed answers.9MIT