shadcn-vue-mcp
Shadcn-vue MCP Server is a powerful AI-driven tool that helps developers instantly create beautiful, modern UI components through natural language descriptions. It integrates the shadcn-vue component library and tailwindcss, seamlessly connects with mainstream IDEs, and provides a streamlined UI dev
README
<div align="center"> <a href="https://smithery.ai/server/@HelloGGX/shadcn-vue-mcp"> <img src="https://github.com/HelloGGX/tailwindcss-mcp/raw/fast-agent/docs/logo1.png" alt="shadcnVue MCP Logo" max-height="450"> </a>
<br />
A powerful AI Agent tool that helps developers instantly create high-quality UI components
Shadcn-vue MCP Server is a powerful AI-driven tool that helps developers instantly create beautiful, modern UI components through natural language descriptions. It integrates the shadcn-vue component library and tailwindcss, seamlessly connects with mainstream IDEs, and provides a streamlined UI development workflow.
<div align="center"> 🌐 Available Languages: <a href="./docs/README-zh-CN.md"><img src="https://img.shields.io/badge/docs-中文版-yellow" alt="中文文档"></a> </div>
</div>
❌ Without shadcn-vue MCP
Developers face multiple challenges when building UI components:
- ❌ Tedious Development Workflow: Constantly switching between the IDE, official documentation, and browser severely impacts development efficiency and focus.
- ❌ Difficulty in Component Selection: Faced with numerous components from
shadcn-vue, developers struggle to quickly find the best fit for their needs without intelligent recommendations. - ❌ High Repetitive Workload: Involves manually writing extensive boilerplate code and handling various component states and complex interaction logic.
- ❌ Insufficient Quality Assurance: It's easy to overlook quality standards like accessibility (A11y), performance optimization, and best coding practices, leading to inconsistent component quality.
- ❌ High Maintenance Costs: As the project grows, manually maintaining the style, behavior, and dependencies of all components becomes exceptionally difficult, making consistency hard to achieve.
✅ With shadcn-vue MCP
shadcn-vue MCP provides an intelligent UI component development experience that revolutionizes the traditional workflow:
- ✅ One-Stop Development Experience: Complete the entire process—from component selection and coding to preview—without ever leaving your editor, simply by describing your needs in natural language.
- ✅ Intelligent Component Recommendation: The
components-filtertool intelligently analyzes your requirements and recommends the most suitableshadcn-vuecomponents. - ✅ High-Quality Code Auto-Generation:
component-builderautomatically generates high-quality Vue component code that complies withshadcn-vueandtailwindcssstandards, with best practices built-in. - ✅ Built-in Quality Assurance:
component-quality-checkautomatically performs accessibility (A11y) and code quality checks on the generated code, ensuring professional-grade components. - ✅ Instant Documentation and Previews:
component-usage-docprovides real-time component documentation, APIs, and usage examples to get you started immediately. - ✅ Ensures High Design Consistency: All generated components strictly adhere to a unified design specification, ensuring visual and interactive consistency across the entire application and enhancing brand value.
🌟 Features
-
Natural Language Descriptions:
- AI-Powered UI Generation: Create UI components by describing them in natural language
-
Multi-IDE Support:
- Cursor IDE integration for seamless workflows.
- Trae support for advanced AI-driven development.
- VSCode support for a robust coding experience.
- VSCode + Cline integration (Beta) for enhanced collaboration.
-
Modern Component Library:
- Built on the shadcn-vue component library and tailwindcss for modern, responsive designs.
-
TypeScript Support:
- Full TypeScript support ensures type-safe and scalable development.
-
Intelligent Documentation Query:
- Real-time access to detailed shadcn-vue component documentation with integrated previews of usage and best practices.
-
Component Enhancement:
- Accessibility: WCAG 2.1 compliant, keyboard navigation, ARIA support
- Performance: Code splitting, tree shaking, optimized bundles
- Consistency: Unified design system, consistent behavior patterns
- Maintainability: Clean code architecture, well-documented components
- Developer Experience: TypeScript support, hot reload, intuitive APIs
🚀 Getting Started
Prerequisites
Before you begin, ensure you have Node.js installed on your system.
- Recommended Node.js version:
18.20.1or later.
Using a different version might lead to installation errors like
Error: spawnSync code-insiders.cmd EINVAL. Downgrading or upgrading to the recommended version is the best solution.
Qucik install: URL Quick Installation for copilot
First, you need to obtain a unique connection URL from the Smithery service that contains your personal credentials. Visit the shadcn-vue-mcp page on Smithery.
Step 1. Click the Generate URL button on the page.:
<img src="https://raw.githubusercontent.com/HelloGGX/shadcn-vue-mcp/fast-agent/docs/url.png" width="700" >
The system will generate a unique URL for you, which includes an API key for authentication. Copy this entire URL.
Step 2. Open vscode, open copilot and select Agent model, Next, add the URL you just obtained to your IDE's MCP configuration file.
- In your IDE project, find or create the configuration file named mcp.json.
- Add or merge the following JSON object into the servers field of that file.
Step 3: for vscode IDE, Select Add Server
<img src="https://raw.githubusercontent.com/HelloGGX/shadcn-vue-mcp/main/docs/add_server.png" width="600">
Step 4: choose HTTP(HTTP or Server-Sent Events)
<img src="https://raw.githubusercontent.com/HelloGGX/shadcn-vue-mcp/main/docs/choose_mcp_type.png" width="600">
Step 5: paste the URL
Step 6: config like this:
{
"servers": {
"shadcn-vue-mcp": {
"url": "https://server.smithery.ai/@HelloGGX/shadcn-vue-mcp/mcp?api_key=xxxx&profile=linguistic-landfowl-TWeEt8"
}
}
}
Config file locations:
- Cursor:
~/.cursor/mcp.json - Trae:
~/.Trae/mcp.json - Cline:
~/.cline/mcp_config.json - Claude:
~/.claude/mcp_config.json
🛠️ Tool List & Core Features
Component Generation Tools
requirement-structuring- Analyzes natural language requirements
- Converts user needs into structured JSON format
- Considers core functionality and essential features
- Built-in user interaction and edge case analysis
Documentation & Analysis Tools
component-usage-doc- Real-time access to shadcn-vue component documentation
- Interactive preview of component variants
- Built-in markdown rendering in browser
- Detailed API and usage examples
Component Filtering & Management
components-filter- Smart component recommendation system
- Supports multi-language description parsing
- Component relationship analysis
- Usage frequency statistics and weighting
Code Quality & Testing
component-quality-check- Automated code quality assessment
- A11y (Accessibility) compliance checking
- Performance optimization suggestions
- Best practices validation
Smart Code Generation
component-builder- AI-powered component generation
- shadcn-vue and Tailwind CSS integration
- TypeScript type safety
- Built-in best practices implementation
Result Example
User: /ui create a flight display component
AI: Generated code as follows:

User: /check
AI: 
AI: Generated code as follows:
🤝 Contribution Guide
We welcome all forms of contributions! You can help us improve @agent/shadcn-vue by:
- Reporting Bugs: If you find a bug, please create an issue in our GitHub repository.
- Suggesting Enhancements: Have an idea for a new feature or an improvement? Let us know by creating an issue.
- Submitting Pull Requests: We are happy to review and merge pull requests. Before making significant changes, please open an issue first to discuss your ideas.
The source code is open-sourced on GitHub.
👥 Community & Support
- Discord Community - Join our active community
📝 License
Licensed under the Apache 2.0 License.
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。
