About Shadcn UI MCP Server
Shadcn UI MCP Server is an MCP server for looking up and installing shadcn/ui components and blocks from an AI client. It targets developers building frontend interfaces with shadcn/ui and supports npm, pnpm, yarn and bun.
Key features
- 01Lists available shadcn/ui components
- 02Retrieves component documentation
- 03Installs components into a project
- 04Lists and installs blocks
- 05Retrieves block documentation and code
- 06Detects the preferred package manager
Use cases
- 01Asking an AI assistant in the IDE to install shadcn/ui components
- 02Fetching block documentation and code through an MCP client
- 03Installing components in projects that use different package managers
MCP support
This is an MCP server that exposes shadcn/ui component and block lookup and installation as tools, such as list-components and install-component, to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3w ago
This tool takes no parameters.
Details
From the project READMEShadcn UI MCP Server
A powerful and flexible MCP (Model Control Protocol) server designed to enhance the development experience with Shadcn UI components. This server provides a robust foundation for building and managing UI components with advanced tooling and functionality.
Features
Tools
The MCP server provides a set of tools that can be used through the Model Control Protocol:
list-components: Get the list of available shadcn/ui componentsget-component-docs: Get documentation for a specific componentinstall-component: Install a shadcn/ui componentlist-blocks: Get the list of available shadcn/ui blocksget-block-docs: Get documentation for a specific blockinstall-blocks: Install a shadcn/ui block
Functionality
-
Component Management
- List available shadcn/ui components
- Get detailed documentation for specific components
- Install components with support for multiple package managers (npm, pnpm, yarn, bun)
-
Block Management
- List available shadcn/ui blocks
- Get documentation and code for specific blocks
- Install blocks with support for multiple package managers
-
Package Manager Support
- Flexible runtime support for npm, pnpm, yarn, and bun
- Automatic detection of user's preferred package manager
Installation
Prerequisites
- Node.js (v18 or higher)
- npm or yarn package manager
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
{
"mcpServers": {
"shadcn-ui-server": {
"command": "npx",
"args": ["@heilgar/shadcn-ui-mcp-server"]
}
}
}
Windsurf Configuration
Add this to your ./codeium/windsurf/model_config.json:
{
"mcpServers": {
"shadcn-ui-server": {
"command": "npx",
"args": ["@heilgar/shadcn-ui-mcp-server"]
}
}
}
Cursor Configuration
Add this to your .cursor/mcp.json:
{
"mcpServers": {
"shadcn-ui-server": {
"command": "npx",
"args": ["@heilgar/shadcn-ui-mcp-server"]
}
}
}
Development and Debugging
Local Development
- Install dependencies:
npm install
- Build the server:
npm run build
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector for debugging:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser, allowing you to:
- Monitor MCP communication
- Inspect tool calls and responses
- Debug server behavior
- View real-time logs
Related Projects and Dependencies
This project is built using the following tools and libraries:
- Model Context Protocol TypeScript SDK - The official TypeScript SDK for MCP servers and clients
- MCP Inspector - A debugging tool for MCP servers
- Cheerio - Fast, flexible, and lean implementation of core jQuery designed specifically for the server
License
MIT License - feel free to use this project for your own purposes.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.