ui-mcp
Click on "Deploy 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., "@ui-mcprender a sales dashboard with monthly revenue chart"
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.
ui-mcp
MCP server that renders flexible, shadcn-styled UI in your local browser. Agents call render_ui to show dashboards, forms, charts, comparisons, and factual answers with numbers or spatial concepts — not just when building apps.
Quick start
npx ui-mcp initThis will:
Register the MCP server in
.cursor/mcp.json(and.mcp.jsonfor Claude Code)Append agent instructions to
AGENTS.md/CLAUDE.mdso the model defaults to rendering (re-runinitto refresh existing snippets)
Reload your editor MCP settings, then ask your agent to render something visual.
Related MCP server: ggui
Tools
Tool | Description |
| Create and open a UI view in the browser |
| Update an existing view by id |
| List active views and URLs |
| Remove a view |
Modes
html— HTML fragment, wrapped in shadcn/Tailwind shelljsx— React component (ApporComponent), compiled in-browser via Babelpage— Full HTML document (you control everything)
Style
The shell applies shadcn CSS variables and Tailwind semantic colors (bg-background, text-primary, etc.). The model is free to build any layout — no component whitelist.
Manual MCP config
{
"mcpServers": {
"ui-mcp": {
"command": "npx",
"args": ["-y", "ui-mcp"]
}
}
}Environment
Variable | Default | Description |
|
| Preferred backend port |
When should agents render?
There is no universal "after final answer" lifecycle hook across MCP clients. The reliable pattern is project instructions:
npx ui-mcp init— writes AGENTS.md / CLAUDE.md with a render-by-default policyCursor rules / project instructions — reinforce the behavior
Agents should call render_ui for most answers — especially numbers, measurements, comparisons, architecture, and workflows. Skip only for truly single-value replies (e.g. a port number) or when the user asks for text only. Re-run npx ui-mcp init to update an existing project's snippet in place.
Development
npm install
npm run build
node dist/bin/ui-mcp.js initLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Deploy AI-generated HTML/CSS/JS to instant public HTTPS URLs from any MCP-compatible agent.
MCP tools for AI agents: render URLs to image/PDF, check link health, convert HTML/CSV/JSON.
Agent-native launch platform and tool directory: search, alternatives, trending, launch via MCP.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to render interactive user interfaces such as forms, dashboards, charts, tables, and wizards directly in MCP-compatible clients. Supports structured data collection and richer interactions beyond text responses.6MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to generate and serve ephemeral, interactive user interfaces over MCP through natural language descriptions.42Apache 2.0
- FlicenseAqualityBmaintenanceMCP server that lets agents create, display, and export rich UI widgets (cards, dashboards, charts, forms) inline in conversations, with interactive iframe support in MCP Apps hosts and PNG image fallback for other clients.3-
- FlicenseNot gradedqualityCmaintenanceEnables rendering interactive UI widgets and data visualizations for Claude.ai through MCP, supporting callback-based forms and client-side charts.-