ui-layouts-mcp
Enables AI assistants to search, understand, and retrieve UI components from ui-layouts.com through tools like search, documentation, metadata, and source code access.
README
@ui-layouts/mcp
@ui-layouts/mcp provides AI assistants with several valuable tools to help them search, understand, and retrieve UI components from ui-layouts.com.
Each tool can be used independently, but they are designed to work together as a complete "component exploration pipeline."
📦 Installation & MCP Setup
Requirements
- Node.js: >=20.10.0
- MCP Client: Claude Desktop, Cursor, or compatible MCP client
Quick Start
Run @ui-layouts/mcp without installing it globally using npx. This is the recommended way to get started:
{
"mcpServers": {
"ui-layouts-mcp": {
"type": "stdio",
"command": "npx",
"args": ["@ui-layouts/mcp"]
}
}
}
💡 Note:
npxwill automatically download and run the latest version of@ui-layouts/mcpwhen needed. No global installation required!
Using with Claude Code (CLI)
claude mcp add ui-layouts-mcp --scope user -- npx -y @ui-layouts/mcp
This registers the MCP server under the CLI-safe name ui-layouts-mcp while still using the @ui-layouts/mcp npm package.
🛠️ Tools
🔍 search_components
Search through the ui-layouts.com component registry by component name, key, group, tags, or href. It performs intelligent matching to find components that meet your criteria and returns detailed information about each match.
When it's useful
- To find a specific UI component by name or tag
- To explore available components by category
- To discover components with particular design or functional features
📘 get_docs
Fetch the complete documentation for a component from ui-layouts.com. You can choose how much content to return, including:
raw_html— the original HTML of the documentation pagetext— plain text extracted from HTMLsnippet— the main section (e.g.<article>or<main>content only)
When it's useful
- To read implementation guides and examples
- To view a component’s structure, props, or variants
- To extract technical explanations for AI-assisted reasoning or integration
🧩 get_component_meta
Fetch structured HTML metadata for a specific component from ui-layouts.com.
It includes fields such as title, description, keywords, Open Graph, Twitter card,
and even custom metadata like component-names and available-components.
When it's useful
- To understand a component’s intent or SEO context
- To generate previews or summaries automatically
- To retrieve linked
componentNamesfor source code lookup
💾 get_source_code
Fetch the actual TypeScript/React source code of a component directly from
https://ui-layouts.com/r/{component}.json.
The tool reads the files[].content field from the JSON registry and returns the .tsx implementation.
When it's useful
- To review or analyze the source code of a component
- To use the component implementation as a code example
- To verify that a component matches your design or API expectations
💬 Prompts
The MCP server also provides reusable prompt templates that guide AI assistants to perform complex tasks using the available tools.
🎯 find_component
Help find the best ui-layouts component(s) for specific requirements, use cases, or design needs.
Parameters:
requirements: What you need (e.g. 'collapsible content sections with smooth animation')tags(optional): Comma-separated tags to filter by (e.g. 'interactive,layout')maxCandidates(optional): Max candidates to fetch docs for (default: '3', range: 1-10)
What it does:
- Generates multiple search queries with synonyms
- Calls
search_componentsmultiple times and merges results - Fetches documentation for top candidates using
get_docs - Provides structured recommendations with:
- Recommended: name/key/href/tags, why, trade-offs
- Alternatives: 1-3 alternative options
- Next steps: Exact tool calls to continue
Strategy:
- Uses intelligent search with synonyms (e.g. accordion/collapse/disclosure)
- Prioritizes components matching provided tags
- Ranks by relevance and compares multiple candidates
🛠️ implement_component
Get a step-by-step implementation guide for a ui-layouts component, including code examples, integration steps, and best practices.
Parameters:
componentKey(optional): Component key (e.g. 'accordion', 'sparkles-title')componentHref(optional): Component href (e.g. '/components/accordion')framework(optional): Target framework (e.g. 'react', 'next', 'vite', 'general', default: 'react')includeSourceCode(optional): Whether to include source code ('true' or 'false', default: 'true')
What it does:
- Fetches component documentation, metadata, and optionally source code
- Generates a comprehensive implementation guide with:
- Overview: Component purpose, features, and when to use
- Installation: Dependencies and setup for the target framework
- Basic Usage: Minimal working example with explanations
- Configuration: Available props and customization options
- Advanced Examples: Real-world use cases with code
- Integration: Framework-specific setup and patterns
- Styling & Customization: Theming and appearance customization
- Best Practices: Performance tips, accessibility, common pitfalls
- Troubleshooting: Common issues and solutions
Output:
- Practical, copy-paste ready code examples
- Framework-specific integration guidance
- Real code from source when available
🔗 Recommended Workflow
💡 Tip: Combine these tools for a full exploration experience:
search_components → get_docs → get_component_meta → get_source_code
| Step | Description | Example |
|---|---|---|
| ① | Find components matching a keyword or tag | search_components { "q": "accordion" } |
| ② | Fetch their documentation (HTML/Text) | get_docs { "key": "accordion", "format": "snippet" } |
| ③ | Retrieve metadata & component links | get_component_meta { "key": "accordion" } |
| ④ | Get TSX source code from registry | get_source_code { "componentName": "single-layout-accordion" } |
⚙️ Server Info
- MCP server name (alias):
ui-layouts-mcp - npm package:
@ui-layouts/mcp - Version:
0.3.0 - Transport:
stdio - Base URL: https://ui-layouts.com
🧠 Example Usage in Cursor / Claude
> call tool search_components { "q": "slider" }
> call tool get_docs { "key": "align-slider" }
> call tool get_component_meta { "key": "align-slider" }
> call tool get_source_code { "componentName": "align-slider" }
👤 Author (Naymur & Jinho)
- X: @naymur_dev
- LinkedIn: in/naymur-rahman
- LinkedIn: in/jinho-yeom
Be A Sponsor
<a href="https://buymeacoffee.com/uilayouts"> <img align="left" src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" height="50" width="210" alt="naymur-uilayout" /></a> <br/>
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.