Untitledui Mcp
@sbilde
About Untitledui Mcp
An MCP for Untitled UI components.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"untitledui": {
"command": "npx",
"args": [
"untitledui-mcp"
],
"env": {
"UNTITLEDUI_LICENSE_KEY": "<your-key>"
}
}
}
}Tools
10List all available component categories (application, base, marketing, etc.)
List components in a category. Use subfolder for variants (e.g., type='application', subfolder='modals')
Search for components by name across all categories
Get a single component's code with token estimates. Returns estimatedTokens and file list. If estimatedTokens > 25000, consider using get_component_file for specific files instead.
Get a component with all base dependencies. Returns estimatedTokens. If response is too large (>25000 tokens), use get_component_file to fetch specific files individually.
Get a single file from a component. Use this when get_component or get_component_with_deps returns a large response (>25000 tokens). First call get_component to see the file list, then fetch specific files as needed.
Browse available page examples. Call without path to see categories, then drill down.
Get a single example page with all files. Requires full path including page number.
Verify that the license key is valid
Clear cached data. Optionally specify a pattern to clear specific entries.
Overview
What is Untitledui Mcp?
Untitledui Mcp is an MCP server that lets AI agents fetch real UntitledUI components instead of generating UI from scratch. It provides direct access to a professionally designed component library, including base components and Pro components.
How to use Untitledui Mcp?
Start with a UntitledUI starter kit (Next.js or Vite) cloned from GitHub. Then add the MCP server via Claude Code CLI or by editing .cursor/mcp.json for Cursor/VS Code. Optionally authenticate for Pro components using npx untitledui@latest login or by setting UNTITLEDUI_LICENSE_KEY. Verify setup with npx untitledui-mcp --test.
Key features of Untitledui Mcp
- AI agents fetch real UntitledUI components instead of generating UI.
- Provides tools: search_components, list_components, get_component_with_deps, etc.
- Base components available without authentication.
- Pro components (modals, sidebars, dashboards) require a license.
- Responses include token estimates to manage context limits.
- Starter kits include Tailwind config and design tokens.
Use cases of Untitledui Mcp
- Recreate any UI from a screenshot using matching UntitledUI components.
- Build complete pages like a SaaS pricing page in seconds.
- Set up an app shell with collapsible sidebar and user dropdown.
- Clone a dashboard page from UntitledUI's templates.
- Mix and match components to create settings pages.
FAQ from Untitledui Mcp
What base components are available without authentication?
Button, input, select, avatar, badge, and similar base components are available without authentication.
How do I authenticate for Pro components?
Run npx untitledui@latest login to open a browser and save your license key, or set UNTITLEDUI_LICENSE_KEY in your MCP config environment.
Why don't components look right after fetching?
Components use custom Tailwind classes and design tokens. Use a UntitledUI starter kit which includes the required Tailwind configuration and tokens.
What are the system requirements for Untitledui Mcp?
Node.js 18+ is required. An UntitledUI Pro license is optionally needed for Pro components.
How does the server handle large component responses?
Responses include token estimates. For components over ~25K tokens, the AI can use get_component_file to fetch individual files.
More Other MCP servers
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
Core Philosophy: Connect, Unify, Respond
mindsdbDelegate anything. It comes back done.
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Comments