Uiverse MCP Tool
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Uiverse MCP ToolExtract HTML from https://uiverse.io/Na3ar-17/evil-dragon-24"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Uiverse MCP Tool
A FastMCP-based code extraction tool for Uiverse.io, supporting component code extraction from Uiverse website for various frontend frameworks.
Features
🎨 Support for multiple frontend framework code extraction
🚀 Built on FastMCP, supporting both stdio and SSE transport methods
🔧 Easy integration with AI workflows
📦 Uses Playwright for web content extraction
Related MCP server: componentize
Supported Frameworks
HTML/CSS
React
Vue
Svelte
Lit
System Requirements
Python >= 3.12
uv package manager
Installation
1. Clone or download the project
git clone https://github.com/YBMecho/Uiverse_MCP.git
cd Uiverse_MPC2. Install dependencies
Using uv to install dependencies:
uv sync3. Install Playwright browsers
uv run playwright installConfiguration
This tool supports two MCP configuration methods: stdio and SSE. Please add one of the following configurations to your MCP configuration file (such as Cursor's mcp.json).
Method 1: stdio configuration (recommended)
{
"mcpServers": {
"uiverse-MCP-tool-stdio": {
"name": "Uiverse MCP Tool",
"type": "stdio",
"description": "Uiverse MCP Tool",
"isActive": true,
"command": "uv",
"args": [
"--directory",
"D:\\YBMecho\\Desktop\\Uiverse_MPC",
"run",
"app.py"
]
}
}
}Note: Please replace D:\\YBMecho\\Desktop\\Uiverse_MPC with your actual project path.
Method 2: SSE configuration
{
"mcpServers": {
"uiverse-MPC-tool-SSE": {
"name": "Uiverse MCP Tool",
"type": "sse",
"description": "Uiverse MCP Tool",
"isActive": true,
"url": "http://127.0.0.1:8000/sse"
}
}
}Note: An HTTP server must be started before using the SSE method.
Usage
Available Tools
1. parse_and_extract
Extract component code from Uiverse links.
Input format: <framework> <link>
Examples:
HTML https://uiverse.io/Na3ar-17/evil-dragon-24
React https://uiverse.io/username/component-name
Vue https://uiverse.io/username/component-name
Svelte https://uiverse.io/username/component-name
Lit https://uiverse.io/username/component-nameUsage rules:
Links must start with
https://uiverse.io/Links must contain a specific component path (not just the domain)
Framework names are case-insensitive
2. list_supported_frameworks
List all currently supported frameworks.
Returns: List of supported frameworks (Markdown format)
Using with AI Assistants
After configuration, you can use it directly in MCP-supporting AI assistants (like Cursor):
Please extract HTML code from https://uiverse.io/Na3ar-17/evil-dragon-24or
Use React framework to extract code from https://uiverse.io/username/component-nameThe AI assistant will automatically call the parse_and_extract tool to retrieve the code.
Project Structure
Uiverse_MPC/
├── app.py # FastMCP main application
├── browser.py # HTML/CSS extractor
├── browser_React.py # React extractor
├── browser_Vue.py # Vue extractor
├── browser_Svelte.py # Svelte extractor
├── browser_Lit.py # Lit extractor
├── pyproject.toml # Project configuration
├── build_exe.spec # PyInstaller configuration
├── dist/ # Executable output directory
│ └── UiverseExtractor.exe
└── README.mdBuilding Executable
The project includes PyInstaller configuration to build a standalone Windows executable:
pyinstaller build_exe.specThe generated UiverseExtractor.exe will be located in the dist/ directory.
Dependencies
mcp[cli]>= 1.16.0 - MCP protocol supportfastmcp>= 2.0.0 - FastMCP frameworkplaywright>= 1.55.0 - Browser automation
Development Notes
Local Running
Run in stdio mode:
uv run app.pyAdding Support for New Frameworks
Create a new
browser_<Framework>.pyfileImplement the
extract_<framework>_code(url: str) -> strasync functionImport and add it to the
_dispatch_extractfunction inapp.pyUpdate the
SUPPORTED_FRAMEWORKSlist
License
Please add the appropriate license information according to your needs.
Contributions
Issues and Pull Requests are welcome!
Contact
For questions or suggestions, please provide feedback through Issues.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityFmaintenanceShadcn-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 devLast updated5327109Apache 2.0
- Alicense-qualityCmaintenanceConverts design screenshots into reusable Tailwind HTML components via MCP protocol, enabling any AI to extract and export individual UI elements.Last updated221MIT
- FlicenseAqualityDmaintenanceCaptures webpage styles and HTML, converts CSS to Tailwind, and applies extracted designs to frontend frameworks like React.Last updated34
- FlicenseAqualityDmaintenanceHarvests React components from Aceternity UI and Shadcn UI, fetching code and metadata to generate integration prompts for AI agents.Last updated67
Related MCP Connectors
Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web
Turn any live website into brand colors, fonts, design tokens, SVGs, Lottie and paste-ready code.
UI design from prompts, screenshots, and URLs for AI coding agents and theme tokens.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/YBMecho/Uiverse_MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server