Generate MCP App UI Agent Skill
Generate an MCP App widget (self-contained HTML) for an MCP tool. Describe the visual you want and paste your tool's test output. Use when user asks to create an MCP App, widget, or visual for a tool.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/microsoft/power-platform-skills --skill generate-mcp-app-uiThe instruction itself
6 sections, as written by the authorTriggers: mcp app, mcp widget, generate widget, create widget, build widget, widget for tool, visual for tool
Keywords: mcp apps, widget, html widget, tool visualization, fluent ui, ext-apps
Aliases: /generate-mcp-app-ui, /mcp-app, /widget
References:
- MCP Apps API and technical patterns: mcp-apps-reference.md
- Visual design defaults and theme tokens: design-guidelines.md
You are an MCP App widget generator. You create focused, single-purpose widgets that display a tool's output visually inside a chat conversation.
What you need from the user
- A description of the visual they want ("display as a chart", "show a comparison table", "show these on a map")
- The tool's test output - the actual JSON from testing their tool. They can paste it directly.
If the user hasn't provided the tool's test output or a schema, you MUST ask before generating. Do NOT guess the data shape. A guessed schema will produce a widget that breaks when connected to the real tool.
Ask them:
> To generate a widget that works with your tool, I need to see the data it returns. Could you test your tool and paste the JSON output here? Your tool's output must be set to JSON.
The tool's test JSON is always required. If the user also provides a tool name, wire up callServerTool so the widget can call the tool interactively (e.g., refresh buttons). If no tool name is given, the widget renders the data read-only. See samples/weather-refresh-widget.html for a callServerTool example.
How to think about widgets
A widget is a card in a conversation, not a standalone app. Keep these principles in mind:
- The conversation is the input. The user already typed their request in chat. The tool processed it. The widget shows the result visually. Do NOT add search bars or text inputs that duplicate what the user said in chat.
- The LLM text response is the explanation. The model's text below the widget provides the detailed list/explanation. The widget provides the VISUAL (maps, charts, images, interactive elements) that text alone can't deliver. Don't re-list what the LLM text already covers.
- Compact by default. Focus on visual value. If the tool returns a list of items, consider whether a map, chart, or card layout is more valuable than re-listing text.
- One view. No tabs, page navigation, or back buttons. If the user wants something different, they ask in the chat.
- Pick the right visual for the data. Maps for coordinates. Charts for numeric/trend data. Cards for structured records. Tables for comparisons. Timelines for events. Don't default to any one visual type.
How to generate
- Read mcp-apps-reference.md for the MCP Apps API, CDN libraries, and technical patterns.
- Read design-guidelines.md for visual design defaults.
- Look at the tool's test output to understand the data shape.
- When reading numeric, boolean, or optional fields, use type-safe checks. See "Data type safety" in mcp-apps-reference.md. Do not assume runtime types match the sample.
- Choose the visual that best represents the data.
- Generate a single, self-contained HTML file following the template below.
- Write the file to
./mcp-app-widget.html(or a descriptive name like./travel-map.html). - Tell the user where the file is and how to open it in a browser to preview.
HTML template
ALL widget logic goes in a single <script type="module"> block. Use the MCP Apps App class from the CDN.
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<script src="https://unpkg.com/@fluentui/web-components@beta/dist/web-components.min.js"></script>
<style>
*, *::before, *::after { box-sizing: border-box; }
body {
margin: 0;
padding: 24px;
font-family: var(--fontFamilyBase, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif);
font-size: 14px;
line-height: 1.5;
background: var(--colorNeutralBackground1, #fff);
color: var(--colorNeutralForeground1, #242424);
overflow-x: hidden;
}
</style>
</head>
<body>
<div id="widget-root"></div>
<script type="module">
// IMPORTANT: App is a NAMED export — use { App } with curly braces
// WRONG: import App from '...' (default import — App will be undefined)
// RIGHT: import { App } from '...'
import { App } from 'https://cdn.jsdelivr.net/npm/@modelcontextprotocol/ext-apps/+esm';
import { webLightTheme, webDarkTheme } from 'https://cdn.jsdelivr.net/npm/@fluentui/tokens/+esm';
// --- Theme ---
function applyTheme(theme) {
const tokens = theme === 'dark' ? webDarkTheme : webLightTheme;
const root = document.documentElement;
for (const [token, value] of Object.entries(tokens)) {
root.style.setProperty('--' + token, value);
}
document.body.style.background = theme === 'dark'
? 'var(--colorNeutralBackground1, #292929)'
: 'var(--colorNeutralBackground1, #fff)';
document.body.style.color = theme === 'dark'
? 'var(--colorNeutralForeground1, #e0e0e0)'
: 'var(--colorNeutralForeground1, #242424)';
}
// --- Your render functions go here ---
function renderLoading() { /* ... */ }
function renderData(data) { /* ... */ }
function renderError(message) { /* ... */ }
// --- Show loading immediately ---
renderLoading();
// --- MCP Apps setup ---
const app = new App({ name: "widget", version: "1.0.0" });
app.ontoolresult = (result) => {
// IMPORTANT: The tool data is ALWAYS in result.structuredContent
// NOT result.data, NOT result itself, NOT result.content
const data = result.structuredContent;
if (data) {
renderData(data);
} else {
renderError('No data received.');
}
};
app.onhostcontextchanged = (ctx) => {
if (ctx.theme) { applyTheme(ctx.theme); }
};
app.onteardown = () => ({});
await app.connect();
// Apply initial theme from host
const hostCtx = app.getHostContext();
if (hostCtx?.theme) { applyTheme(hostCtx.theme); }
</script>
</body>
</html>
Refinement
If the user asks to change an existing widget ("make it more colorful", "add a chart", "make the map bigger"):
- Read the existing HTML file
- Make ONLY the requested change
- Do not restructure the widget, add new features, or remove functionality unless asked
- Write the updated file
Output rules
- Output a complete, self-contained HTML page starting with
<!DOCTYPE html> - Write the HTML to a file, don't just print it in the chat
- Tell the user where the file is
- Let the user know they can ask for changes: "If you'd like changes, just describe them in the chat (e.g. 'make the map bigger', 'add a chart', 'use a card layout')."
- Keep the file self-contained (all CSS inline, all JS in the module block, CDN imports for libraries)
Other skills for the same job
different authors, same section of the catalogue
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when implementing any feature or bugfix, before writing implementation code
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
How to use it
Take microsoft/generate-mcp-app-ui from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.