MCP UI/UX Prompt Refiner
Transforms basic interface ideas into comprehensive, professional-grade UI/UX design specifications with detailed styling, animations, components, and accessibility requirements for websites, apps, and other digital interfaces.
README
MCP UI/UX Prompt Refiner
An MCP (Model Context Protocol) server that transforms basic interface prompts into world-class UI/UX design specifications. This tool helps you break free from generic AI-generated designs by outputting comprehensive, professional-grade design prompts.
Features
- 5 Specialized Tools for different aspects of UI/UX design
- 4 Knowledge Resources covering design principles, animations, UX patterns, and templates
- 11 Pre-configured Prompts for common interface types
- Supports websites, mobile apps, desktop apps, CLI tools, presentations, and more
Installation
npm install
npm run build
Usage
With Cursor/Claude
Add to your MCP settings (.cursor/mcp.json or Claude Desktop config):
{
"mcpServers": {
"ui-prompt-refiner": {
"command": "node",
"args": ["path/to/mcp-ui-prompt-refiner/dist/server.js"]
}
}
}
Development Mode
npm run dev
Available Tools
1. refine_ui_prompt (Primary Tool)
Transform a basic interface idea into a comprehensive design specification.
Parameters:
rawPrompt(required): Your basic interface ideainterfaceType: Type of interface (auto-detected if not provided)style: Design style (minimalist, bold-experimental, etc.)colorMood: Color palette mood (energetic, calm, professional, etc.)animationIntensity: Level of animation (subtle, moderate, dramatic, cinematic)targetAudience: Who will use this interfacebrandKeywords: Keywords describing the brand
2. analyze_interface
Analyze an interface request to detect type, suggest styles, and identify components.
3. compose_animations
Generate detailed animation specifications with CSS examples.
4. generate_ux_flow
Create user journey maps with interaction patterns and accessibility requirements.
5. suggest_tech_stack
Get technology recommendations based on interface type and design requirements.
Interface Types Supported
website-landing- Conversion-focused landing pageswebsite-saas- SaaS marketing websiteswebsite-portfolio- Portfolio/showcase websiteswebsite-ecommerce- Online storesdashboard- Analytics and data dashboardsmobile-app- iOS/Android applicationsdesktop-app- Desktop applicationscli-terminal- Command-line interfacespresentation- Slide decksadmin-panel- Backend management interfacessocial-platform- Social networking interfaces
Design Styles
minimalist- Clean, whitespace-focusedbold-experimental- Creative, unconventionalcorporate-professional- Business-appropriateplayful-creative- Fun, colorfulluxury-elegant- Premium, sophisticatedtech-futuristic- Modern, digitalorganic-natural- Earth-toned, flowingbrutalist- Raw, industrialretro-vintage- Nostalgicglassmorphic- Frosted glass effectsneumorphic- Soft shadow depth
Resources
Access design knowledge via MCP resources:
design://principles- Gestalt, hierarchy, color theorydesign://animation-patterns- Easing functions, entry/scroll animationsdesign://ux-patterns- Navigation, feedback, forms, accessibilitydesign://interface-templates- Templates for each interface type
Example
User: "I need a landing page for my AI writing tool"
→ refine_ui_prompt generates:
- Complete design specification
- Color palette with psychology
- Typography system
- Component specifications
- Animation choreography
- UX flow guidelines
- Accessibility requirements
- Implementation priorities
Output Format
All tools output structured markdown that can be:
- Saved directly to a file
- Used as a prompt for implementation
- Shared with design tools or team members
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。