Create MCP App
Provides scaffolding and guidance for building interactive, resource-backed UI applications within MCP-enabled environments.
Install
mkdir -p .claude/skills/create-mcp-app-majiayu000 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14392" && unzip -o skill.zip -d .claude/skills/create-mcp-app-majiayu000 && rm skill.zipInstalls to .claude/skills/create-mcp-app-majiayu000
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.Key capabilities
- →Scaffold new MCP Apps using various frontend frameworks
- →Register MCP tools with associated HTML resources
- →Handle MCP App lifecycle events like `ontoolinput` and `onhostcontextchanged`
- →Control tool visibility for model or UI-only interactions
- →Stream partial input for large data processing
- →Update model context based on UI state
How it works
An MCP App combines an MCP tool with an HTML resource, allowing the host to call the tool, receive data, and render an interactive UI that can process inputs and update the model context.
Inputs & outputs
When to use Create MCP App
- →Create interactive MCP tool UI
- →Scaffold MCP application
- →Register custom MCP resources
About this skill
Create MCP App
Build interactive UIs that run inside MCP-enabled hosts like Claude Desktop. An MCP App combines an MCP tool with an HTML resource to display rich, interactive content.
Core Concept: Tool + Resource
Every MCP App requires two parts linked together:
- Tool - Called by the LLM/host, returns data
- Resource - Serves the bundled HTML UI that displays the data
- Link - The tool's
_meta.ui.resourceUrireferences the resource
Host calls tool → Server returns result → Host renders resource UI → UI receives result
Quick Start Decision Tree
Framework Selection
| Framework | SDK Support | Best For |
|---|---|---|
| React | useApp hook provided | Teams familiar with React |
| Vanilla JS | Manual lifecycle | Simple apps, no build complexity |
| Vue/Svelte/Preact/Solid | Manual lifecycle | Framework preference |
Project Context
Adding to existing MCP server:
- Import
registerAppTool,registerAppResourcefrom SDK - Add tool registration with
_meta.ui.resourceUri - Add resource registration serving bundled HTML
Creating new MCP server:
- Set up server with transport (stdio or HTTP)
- Register tools and resources
- Configure build system with
vite-plugin-singlefile
Getting Reference Code
Clone the SDK repository for working examples and API documentation:
git clone --branch "v$(npm view @modelcontextprotocol/ext-apps version)" --depth 1 https://github.com/modelcontextprotocol/ext-apps.git /tmp/mcp-ext-apps
Framework Templates
Learn and adapt from /tmp/mcp-ext-apps/examples/basic-server-{framework}/:
| Template | Key Files |
|---|---|
basic-server-vanillajs/ | server.ts, src/mcp-app.ts, mcp-app.html |
basic-server-react/ | server.ts, src/mcp-app.tsx (uses useApp hook) |
basic-server-vue/ | server.ts, src/App.vue |
basic-server-svelte/ | server.ts, src/App.svelte |
basic-server-preact/ | server.ts, src/mcp-app.tsx |
basic-server-solid/ | server.ts, src/mcp-app.tsx |
Each template includes:
- Complete
server.tswithregisterAppToolandregisterAppResource - Client-side app with all lifecycle handlers
vite.config.tswithvite-plugin-singlefilepackage.jsonwith all required dependencies.gitignoreexcludingnode_modules/anddist/
API Reference (Source Files)
Read JSDoc documentation directly from /tmp/mcp-ext-apps/src/:
| File | Contents |
|---|---|
src/app.ts | App class, handlers (ontoolinput, ontoolresult, onhostcontextchanged, onteardown), lifecycle |
src/server/index.ts | registerAppTool, registerAppResource, tool visibility options |
src/spec.types.ts | All type definitions: McpUiHostContext, CSS variable keys, display modes |
src/styles.ts | applyDocumentTheme, applyHostStyleVariables, applyHostFonts |
src/react/useApp.tsx | useApp hook for React apps |
src/react/useHostStyles.ts | useHostStyles, useHostStyleVariables, useHostFonts hooks |
Advanced Examples
| Example | Pattern Demonstrated |
|---|---|
examples/shadertoy-server/ | Streaming partial input + visibility-based pause/play (best practice for large inputs) |
examples/wiki-explorer-server/ | callServerTool for interactive data fetching |
examples/system-monitor-server/ | Polling pattern with interval management |
examples/video-resource-server/ | Binary/blob resources |
examples/sheet-music-server/ | ontoolinput - processing tool args before execution completes |
examples/threejs-server/ | ontoolinputpartial - streaming/progressive rendering |
examples/map-server/ | updateModelContext - keeping model informed of UI state |
examples/transcript-server/ | updateModelContext + sendMessage - background context updates + user-initiated messages |
examples/basic-host/ | Reference host implementation using AppBridge |
Critical Implementation Notes
Adding Dependencies
Use npm install to add dependencies rather than manually writing version numbers:
npm install @modelcontextprotocol/ext-apps @modelcontextprotocol/sdk zod
This lets npm resolve the latest compatible versions. Never specify version numbers from memory.
TypeScript Server Execution
Use tsx as a devDependency for running TypeScript server files:
npm install -D tsx
"scripts": {
"serve": "tsx server.ts"
}
Note: The SDK examples use bun but generated projects should use tsx for broader compatibility.
Handler Registration Order
Register ALL handlers BEFORE calling app.connect():
const app = new App({ name: "My App", version: "1.0.0" });
// Register handlers first
app.ontoolinput = (params) => { /* handle input */ };
app.ontoolresult = (result) => { /* handle result */ };
app.onhostcontextchanged = (ctx) => { /* handle context */ };
app.onteardown = async () => { return {}; };
// Then connect
await app.connect();
Tool Visibility
Control who can access tools via _meta.ui.visibility:
// Default: visible to both model and app
_meta: { ui: { resourceUri, visibility: ["model", "app"] } }
// UI-only (hidden from model) - for refresh buttons, form submissions
_meta: { ui: { resourceUri, visibility: ["app"] } }
// Model-only (app cannot call)
_meta: { ui: { resourceUri, visibility: ["model"] } }
Host Styling Integration
Vanilla JS - Use helper functions:
import { applyDocumentTheme, applyHostStyleVariables, applyHostFonts } from "@modelcontextprotocol/ext-apps";
app.onhostcontextchanged = (ctx) => {
if (ctx.theme) applyDocumentTheme(ctx.theme);
if (ctx.styles?.variables) applyHostStyleVariables(ctx.styles.variables);
if (ctx.styles?.css?.fonts) applyHostFonts(ctx.styles.css.fonts);
};
React - Use hooks:
import { useApp, useHostStyles } from "@modelcontextprotocol/ext-apps/react";
const { app } = useApp({ appInfo, capabilities, onAppCreated });
useHostStyles(app); // Injects CSS variables to document, making var(--*) available
Using variables in CSS - After applying, use var():
.container {
background: var(--color-background-secondary);
color: var(--color-text-primary);
font-family: var(--font-sans);
border-radius: var(--border-radius-md);
}
.code {
font-family: var(--font-mono);
font-size: var(--font-text-sm-size);
line-height: var(--font-text-sm-line-height);
color: var(--color-text-secondary);
}
.heading {
font-size: var(--font-heading-lg-size);
font-weight: var(--font-weight-semibold);
}
Key variable groups: --color-background-*, --color-text-*, --color-border-*, --font-sans, --font-mono, --font-text-*-size, --font-heading-*-size, --border-radius-*. See src/spec.types.ts for full list.
Safe Area Handling
Always respect safeAreaInsets:
app.onhostcontextchanged = (ctx) => {
if (ctx.safeAreaInsets) {
const { top, right, bottom, left } = ctx.safeAreaInsets;
document.body.style.padding = `${top}px ${right}px ${bottom}px ${left}px`;
}
};
Streaming Partial Input
For large tool inputs, use ontoolinputpartial to show progress during LLM generation. The partial JSON is healed (always valid), enabling progressive UI updates.
Spec: ui/notifications/tool-input-partial
app.ontoolinputpartial = (params) => {
const args = params.arguments; // Healed partial JSON - always valid, fields appear as generated
// Use args directly for progressive rendering
};
app.ontoolinput = (params) => {
// Final complete input - switch from preview to full render
};
Use cases:
| Pattern | Example |
|---|---|
| Code preview | Show streaming code in <pre>, render on complete (examples/shadertoy-server/) |
| Progressive form | Fill form fields as they stream in |
| Live chart | Add data points to chart as array grows |
| Partial render | Render incomplete structured data (tables, lists, trees) |
Simple pattern (code preview):
app.ontoolinputpartial = (params) => {
codePreview.textContent = params.arguments?.code ?? "";
codePreview.style.display = "block";
canvas.style.display = "none";
};
app.ontoolinput = (params) => {
codePreview.style.display = "none";
canvas.style.display = "block";
render(params.arguments);
};
Visibility-Based Resource Management
Pause expensive operations (animations, WebGL, polling) when view scrolls out of viewport:
const observer = new IntersectionObserver((entries) => {
entries.forEach((entry) => {
if (entry.isIntersecting) {
animation.play(); // or: startPolling(), shaderToy.play()
} else {
animation.pause(); // or: stopPolling(), shaderToy.pause()
}
});
});
observer.observe(document.querySelector(".main"));
Fullscreen Mode
Request fullscreen via app.requestDisplayMode(). Check availability in host context:
let currentMode: "inline" | "fullscreen" = "inline";
app.onhostcontextchanged = (ctx) => {
// Check if fullscreen available
if (ctx.availableDisplayModes?.includes("fullscreen")) {
fullscreenBtn.style.display = "block";
}
// Track current mode
if (ctx.displayMode) {
currentMode = ctx.displayMode;
container.classList.toggle("fullscreen", currentMode === "fullscreen");
}
};
async function toggleFullscreen() {
const newMode = currentMode === "fullscreen" ? "inline" : "fullscreen";
const result = await app.requestDisplayMode({ mode: newMode });
currentMode = result.mode;
}
CSS pattern - Remove border radius in fullscreen:
.main { border-radius: var(--border-radius-lg); overflow: hidden; }
.main.fullscreen { border-radius: 0; }
See `examples/shade
Content truncated.
When not to use it
- →When building applications that do not interact with MCP-enabled hosts
- →When the application does not require an interactive UI linked to an MCP tool
- →When the user is not asking to create or modify an MCP App
Limitations
- →Requires an MCP-enabled host to run the interactive UI
- →Tool and resource must be explicitly linked via `_meta.ui.resourceUri`
- →All handlers must be registered before calling `app.connect()`
How it compares
This skill provides structured guidance and templates for building interactive UIs that integrate directly with MCP tools and hosts, unlike standalone applications that lack this specific protocol for host interaction.
Compared to similar skills
Create MCP App side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| Create MCP App (this skill) | 0 | 3mo | Review | Advanced |
| mcp-builder | 136 | 3mo | Review | Advanced |
| mcp-integration | 21 | 8mo | Review | Intermediate |
| opencode-orchestrator-creator | 8 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by majiayu000
View all by majiayu000 →You might also like
mcp-builder
anthropics
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
mcp-integration
anthropics
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
opencode-orchestrator-creator
IgorWarzocha
Creates universal OpenCode orchestrator folder structure with specialized agent that can manage swarm servers via curl commands
claude-opus-4-5-migration
anthropics
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
mcp-management
mrgoonie
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
n8n-mcp-orchestrator
manutej
Expert MCP (Model Context Protocol) orchestration with n8n workflow automation. Master bidirectional MCP integration, expose n8n workflows as AI agent tools, consume MCP servers in workflows, build agentic systems, orchestrate multi-agent workflows, and create production-ready AI-powered automation pipelines with Claude Code integration.