This server provides deterministic design style intelligence for AI content generation pipelines, offering two core tools:
recommend_style: Get a data-driven style recommendation by providing a campaign objective (e.g., product_launch, brand_awareness), target demographic (e.g., gen_z, executives), and optional brand description and season. The server scores all 30 built-in styles using deterministic fuzzy matching and returns the best match with reasoning and ranked alternatives — no AI inference involved.
get_style: Fetch structured design tokens for any of the 30 curated styles by providing a style slug (e.g., cyberpunk, neo-brutalism, luxury). Returned data includes:
Style name and description
Color palette
Typography rules
Mood tokens
Visual directives
Negative prompts (for image/video generation pipelines)
Available Styles (30): academia, art-deco, bauhaus, bold-typography, botanical, claymorphism, cyberpunk, enterprise, flat-design, industrial, kinetic, luxury, material, maximalism, minimal-dark, modern-dark, monochrome, neo-brutalism, neumorphism, newsprint, organic, playful-geometric, professional, retro, saas, sketch, swiss-minimalist, terminal, vaporwave, web3
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., "@Design Style MCP Server recommend a style for a streetwear brand targeting Gen Z for a product launch"
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.
A Model Context Protocol (MCP) server that provides design style intelligence for AI content generation. Ships with 30 curated design styles — each with color palettes, typography, mood tokens, visual directives, and negative prompts ready for image/video generation pipelines.
No AI inference — pure deterministic scoring against style characteristics.
Tool | Description |
| Deterministic style recommendation based on brand context, campaign objective, target demographic, and season. Returns a top match with scoring reasoning and ranked alternatives. |
| Retrieve structured design tokens for a given style slug: name, description, color palette, typography, mood, visual directives, and negative prompt sections. |
academia, art-deco, bauhaus, bold-typography, botanical, claymorphism, cyberpunk, enterprise, flat-design, industrial, kinetic, luxury, material, maximalism, minimal-dark, modern-dark, monochrome, neo-brutalism, neumorphism, newsprint, organic, playful-geometric, professional, retro, saas, sketch, swiss-minimalist, terminal, vaporwave, web3
Each style includes a full prompt file with design philosophy, color system, typography rules, visual directives, and negative prompts.
Related MCP server: web-stylebook-mcp
Node.js 22.14+
Published package: @luminarylane/design-style-mcp-server on npm
Run without a global install:
npx --yes @luminarylane/design-style-mcp-serverTo run from source:
git clone https://github.com/luminarylane/design-style-mcp-server.git
cd design-style-mcp-server
npm install
npm run build# Development
npm run dev
# Production
npm startAdd to your claude_desktop_config.json:
{
"mcpServers": {
"design-style": {
"command": "npx",
"args": ["--yes", "@luminarylane/design-style-mcp-server"]
}
}
}recommend_styleGiven a brand description, campaign objective, target demographic, and optional season, the server scores all 30 styles against their characteristics (objectives, demographics, industries, moods, seasonal fit) and returns the top match with alternatives.
Input: { objective: "product_launch", demographic: "gen_z", brand: "streetwear" }
Output: { style: "neo-brutalism", reasoning: "...", alternatives: [...] }get_styleGiven a style slug, returns structured tokens extracted from the style's prompt file:
Input: { style: "cyberpunk" }
Output: { name, description, colors, typography, mood, promptAdditions, negativePrompt, reference }Env Var | Default | Description |
|
| Override path to the design-styles data directory |
Transport: stdio (standard MCP protocol)
Data: 30 style prompt files + descriptions index (plain text, bundled)
Scoring: Deterministic fuzzy matching — no AI inference, no network calls
Caching: Prompt files are cached in-memory after first read
Dependencies: Only @modelcontextprotocol/sdk and zod
# Development server (auto-reload)
npm run dev
# Type check
npx tsc --noEmit
# Build
npm run buildAdd the slug to DESIGN_STYLE_SLUGS in src/styles.ts
Add characteristics (objectives, demographics, industries, moods) to STYLE_CHARACTERISTICS
Add a description line to design-styles/descriptions.txt
Create a prompt file at design-styles/prompts/{slug}.txt
The design-style prompt collection was inspired by and initially sourced from designprompts.dev. This project is an independent MCP server and is not affiliated with or endorsed by designprompts.dev.
Retrieve structured design style tokens for AI content generation. Returns name, description, color palette, typography, mood, visual directives, and negative prompt sections extracted from the style's prompt file. Valid slugs: academia, art-deco, bauhaus, bold-typography, botanical, claymorphism, cyberpunk, enterprise, flat-design, industrial, kinetic, luxury, material, maximalism, minimal-dark, modern-dark, monochrome, neo-brutalism, neumorphism, newsprint, organic, playful-geometric, professional, retro, saas, sketch, swiss-minimalist, terminal, vaporwave, web3
Inputs: style (required).
Recommend a design style based on brand context, campaign objective, and target demographic. Returns a top match with reasoning and alternatives. No AI inference — uses deterministic scoring against style characteristics.
Inputs: objective (required), demographic (required), brand, season.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
Both tools have clearly distinct purposes: get_style retrieves details for a known style, recommend_style suggests a style based on context. No overlap.
Both tool names follow the verb_noun pattern (get_style, recommend_style) consistently, making them predictable.
With only 2 tools, the server is minimal but still covers the core functionality for its narrow domain. A list tool would be useful but not mandatory.
Covers retrieval and recommendation, but lacks a tool to list all available style slugs programmatically, which is a notable gap since get_style requires a valid slug.
Design-style library for AI agents: find a style by use or mood, preview it, apply its spec.
Give your agent a real design system: tokens, measured WCAG contrast, and rules to follow.
Curated design references for AI — real CSS values, typography specs, and color palettes.
Build and manage your design system with AI: tokens, themes, components, icons, Figma and code.
