
@jpisnice/shadcn-ui-mcp-server
A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation
Tools
get_component
Get the source code for a specific shadcn/ui v4 component
get_component_demo
Get demo code illustrating how a shadcn/ui v4 component should be used
list_components
Get all available shadcn/ui v4 components
get_component_metadata
Get metadata for a specific shadcn/ui v4 component
get_directory_structure
Get the directory structure of the shadcn-ui v4 repository
get_block
Get source code for a specific shadcn/ui v4 block (e.g., calendar-01, dashboard-01)
list_blocks
Get all available shadcn/ui v4 blocks with categorization
README
Shadcn UI v4 MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to shadcn/ui v4 components, blocks, demos, and metadata. This server enables AI tools like Claude Desktop, Continue.dev, and other MCP-compatible clients to retrieve and work with shadcn/ui components seamlessly.
🚀 Key Features
- Component Source Code: Get the latest shadcn/ui v4 component TypeScript source
- Component Demos: Access example implementations and usage patterns
- Blocks Support: Retrieve complete block implementations (dashboards, calendars, login forms, etc.)
- Metadata Access: Get component dependencies, descriptions, and configuration details
- Directory Browsing: Explore the shadcn/ui repository structure
- GitHub API Integration: Efficient caching and intelligent rate limit handling
📦 Quick Start
⚡ Using npx (Recommended)
The fastest way to get started - no installation required!
# Basic usage (rate limited to 60 requests/hour)
npx @jpisnice/shadcn-ui-mcp-server
# With GitHub token for better rate limits (5000 requests/hour)
npx @jpisnice/shadcn-ui-mcp-server --github-api-key ghp_your_token_here
# Short form
npx @jpisnice/shadcn-ui-mcp-server -g ghp_your_token_here
# Using environment variable
export GITHUB_PERSONAL_ACCESS_TOKEN=ghp_your_token_here
npx @jpisnice/shadcn-ui-mcp-server
🎯 Try it now: Run npx @jpisnice/shadcn-ui-mcp-server --help
to see all options!
🔧 Command Line Options
shadcn-ui-mcp-server [options]
Options:
--github-api-key, -g <token> GitHub Personal Access Token
--help, -h Show help message
--version, -v Show version information
Environment Variables:
GITHUB_PERSONAL_ACCESS_TOKEN Alternative way to provide GitHub token
Examples:
npx @jpisnice/shadcn-ui-mcp-server --help
npx @jpisnice/shadcn-ui-mcp-server --version
npx @jpisnice/shadcn-ui-mcp-server -g ghp_1234567890abcdef
GITHUB_PERSONAL_ACCESS_TOKEN=ghp_token npx @jpisnice/shadcn-ui-mcp-server
🔑 GitHub API Token Setup
Why do you need a token?
- Without token: Limited to 60 API requests per hour
- With token: Up to 5,000 requests per hour
- Better reliability and faster responses
📝 Getting Your Token (2 minutes)
-
Go to GitHub Settings:
- Visit GitHub Settings → Developer settings → Personal access tokens → Tokens (classic)
- Or: GitHub Profile → Settings → Developer settings → Personal access tokens
-
Generate New Token:
- Click "Generate new token (classic)"
- Add a note: "shadcn-ui MCP server"
- Expiration: Choose your preference (90 days recommended)
- Scopes: ✅ No scopes needed! (public repository access is sufficient)
-
Copy Your Token:
- Copy the generated token (starts with
ghp_
) - ⚠️ Save it securely - you won't see it again!
- Copy the generated token (starts with
🚀 Using Your Token
Method 1: Command Line (Quick testing)
npx @jpisnice/shadcn-ui-mcp-server --github-api-key ghp_your_token_here
Method 2: Environment Variable (Recommended)
# Add to your shell profile (~/.bashrc, ~/.zshrc, etc.)
export GITHUB_PERSONAL_ACCESS_TOKEN=ghp_your_token_here
# Then simply run:
npx @jpisnice/shadcn-ui-mcp-server
Method 3: Claude Desktop Configuration
{
"mcpServers": {
"shadcn-ui": {
"command": "npx",
"args": ["@jpisnice/shadcn-ui-mcp-server"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
}
}
}
}
✅ Verify Your Setup
# Test without token (should show rate limit warning)
npx @jpisnice/shadcn-ui-mcp-server --help
# Test with token (should show success message)
npx @jpisnice/shadcn-ui-mcp-server --github-api-key ghp_your_token --help
# Check your current rate limit
curl -H "Authorization: token ghp_your_token" https://api.github.com/rate_limit
🛠️ Available Tools
The MCP server provides these tools for AI assistants:
Component Tools
get_component
- Get component source codeget_component_demo
- Get component usage exampleslist_components
- List all available componentsget_component_metadata
- Get component dependencies and info
Block Tools
get_block
- Get complete block implementations (dashboard-01, calendar-01, etc.)list_blocks
- List all available blocks with categories
Repository Tools
get_directory_structure
- Explore the shadcn/ui repository structure
Example Tool Usage
// These tools can be called by AI assistants via MCP protocol
// Get button component source
{
"tool": "get_component",
"arguments": { "componentName": "button" }
}
// List all components
{
"tool": "list_components",
"arguments": {}
}
// Get dashboard block
{
"tool": "get_block",
"arguments": { "blockName": "dashboard-01" }
}
🔗 Claude Desktop Integration
Add to your Claude Desktop configuration (~/.config/Claude/claude_desktop_config.json
):
{
"mcpServers": {
"shadcn-ui": {
"command": "npx",
"args": ["@jpisnice/shadcn-ui-mcp-server", "--github-api-key", "ghp_your_token_here"]
}
}
}
Or with environment variable:
{
"mcpServers": {
"shadcn-ui": {
"command": "npx",
"args": ["@jpisnice/shadcn-ui-mcp-server"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
}
}
}
}
🐛 Troubleshooting
Common Issues
"Rate limit exceeded" errors:
# Solution: Add GitHub API token
npx @jpisnice/shadcn-ui-mcp-server --github-api-key ghp_your_token_here
"Command not found" errors:
# Solution: Install Node.js 18+ and ensure npx is available
node --version # Should be 18+
npx --version # Should work
Component not found:
# Check available components first
npx @jpisnice/shadcn-ui-mcp-server
# Then call list_components tool via your MCP client
Network/proxy issues:
# Set proxy if needed
export HTTP_PROXY=http://your-proxy:8080
export HTTPS_PROXY=http://your-proxy:8080
npx @jpisnice/shadcn-ui-mcp-server
Debug Mode
Enable verbose logging:
# Set debug environment variable
DEBUG=* npx @jpisnice/shadcn-ui-mcp-server --github-api-key ghp_your_token
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🤝 Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
📞 Support
🔗 Related Projects
- shadcn/ui - The component library this server provides access to
- Model Context Protocol - The protocol specification
- MCP TypeScript SDK - Official MCP SDK
⭐ Acknowledgments
- shadcn for the amazing UI component library
- Anthropic for the Model Context Protocol specification
- The open source community for inspiration and contributions
Made with ❤️ by Janardhan Polle
Star ⭐ this repo if you find it helpful!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.