Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

shadcn-ui-mcp-server

MCP.Pizza Chef: ymadd

The shadcn-ui-mcp-server is a TypeScript-based MCP server that offers structured, cached reference data for shadcn/ui components. It scrapes official documentation and GitHub repos to provide AI models with detailed component descriptions, installation guides, usage examples, props, variants, and code samples. This enables seamless integration of shadcn/ui component knowledge into AI workflows.

Use This MCP server To

Retrieve a list of all shadcn/ui components for UI development Fetch detailed documentation for specific shadcn/ui components Access usage examples to implement shadcn/ui components correctly Search shadcn/ui components by keywords for quick discovery Integrate shadcn/ui component data into AI-powered coding assistants Cache and serve up-to-date shadcn/ui documentation for offline use

README

shadcn-ui MCP Server

MCP server for shadcn/ui component references

This is a TypeScript-based MCP server that provides reference information for shadcn/ui components. It implements a Model Context Protocol (MCP) server that helps AI assistants access shadcn/ui component documentation and examples.

Features

Tools

  • list_shadcn_components - Get a list of all available shadcn/ui components
  • get_component_details - Get detailed information about a specific component
  • get_component_examples - Get usage examples for a specific component
  • search_components - Search for components by keyword

Functionality

This server scrapes and caches information from:

It provides structured data including:

  • Component descriptions
  • Installation instructions
  • Usage examples
  • Props and variants
  • Code samples

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

Claude Desktop Configuration

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Option 1: Using local build
{
  "mcpServers": {
    "shadcn-ui-server": {
      "command": "/path/to/shadcn-ui-server/build/index.js"
    }
  }
}
Option 2: Using npx command
{
  "mcpServers": {
    "shadcn-ui-server": {
      "command": "npx",
      "args": ["-y", "shadcn-ui-mcp-server"]
    }
  }
}

Windsurf Configuration

Add this to your ./codeium/windsurf/model_config.json:

{
  "mcpServers": {
    "shadcn-ui-server": {
      "command": "npx",
      "args": ["-y", "shadcn-ui-mcp-server"]
    }
  }
}

Cursor Configuration

Add this to your .cursor/mcp.json:

{
  "mcpServers": {
    "shadcn-ui-server": {
      "command": "npx",
      "args": ["-y", "shadcn-ui-mcp-server"]
    }
  }
}

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

shadcn-ui-mcp-server FAQ

How does the shadcn-ui-mcp-server obtain component data?
It scrapes and caches data from the official shadcn/ui documentation site and GitHub repository.
What programming language is the shadcn-ui-mcp-server built with?
It is implemented in TypeScript for robust type safety and maintainability.
Can I get usage examples for shadcn/ui components through this server?
Yes, it provides detailed usage examples for each component.
Does the server support searching components by keywords?
Yes, it includes a search_components tool to find components by keyword.
How can I install the shadcn-ui-mcp-server?
You can install dependencies via npm and follow the build instructions in the GitHub repository.
Is the data provided by the server kept up to date?
The server scrapes the latest data from official sources to keep information current.
Can this server be integrated with multiple LLM providers?
Yes, it is compatible with models like OpenAI, Anthropic Claude, and Google Gemini.
What kind of structured data does the server provide?
It offers component descriptions, installation instructions, props, variants, and code samples.