Create Mcp App logo

Create Mcp App

OrganizationPopular
tldraw
create-mcp-app

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.

Overview

Publishertldraw
Repositorytldraw
Skill namecreate-mcp-app
Stars
50.8K
Forks
3.6K
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by tldraw on GitHub. Read the source before you install it.

Installation

Install the Create Mcp App AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/tldraw/tldraw/tree/main/apps/mcp-app/.claude/skills/create-mcp-app
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/tldraw/tldraw.git /tmp/tldraw
mkdir -p .claude/skills
cp -r /tmp/tldraw/apps/mcp-app/.claude/skills/create-mcp-app .claude/skills/create-mcp-app
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Mcp App in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Create Mcp App on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Create Mcp App is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:

  1. Tool - Called by the LLM/host, returns data
  2. Resource - Serves the bundled HTML UI that displays the data
  3. Link - The tool's _meta.ui.resourceUri references the resource
Host calls tool → Server returns result → Host renders resource UI → UI receives result

Quick Start Decision Tree

Framework Selection

FrameworkSDK SupportBest For
ReactuseApp hook providedTeams familiar with React
Vanilla JSManual lifecycleSimple apps, no build complexity
Vue/Svelte/Preact/SolidManual lifecycleFramework preference

Project Context

Adding to existing MCP server:

  • Import registerAppTool, registerAppResource from 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:

bash
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}/:

TemplateKey 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.ts with registerAppTool and registerAppResource
  • Client-side app with all lifecycle handlers
  • vite.config.ts with vite-plugin-singlefile
  • package.json with all required dependencies
  • .gitignore excluding node_modules/ and dist/

API Reference (Source Files)

Read JSDoc documentation directly from /tmp/mcp-ext-apps/src/:

FileContents
src/app.tsApp class, handlers (ontoolinput, ontoolresult, onhostcontextchanged, onteardown), lifecycle
src/server/index.tsregisterAppTool, registerAppResource, tool visibility options
src/spec.types.tsAll type definitions: McpUiHostContext, CSS variable keys, display modes
src/styles.tsapplyDocumentTheme, applyHostStyleVariables, applyHostFonts
src/react/useApp.tsxuseApp hook for React apps
src/react/useHostStyles.tsuseHostStyles, useHostStyleVariables, useHostFonts hooks

Advanced Examples

ExamplePattern 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:

bash
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:

bash
npm install -D tsx
json
"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():

typescript
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:

typescript
// 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:

typescript
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:

typescript
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():

css
.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:

typescript
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

typescript
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:

PatternExample
Code previewShow streaming code in <pre>, render on complete (examples/shadertoy-server/)
Progressive formFill form fields as they stream in
Live chartAdd data points to chart as array grows
Partial renderRender incomplete structured data (tables, lists, trees)

Simple pattern (code preview):

typescript
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:

typescript
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:

typescript
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:

css
.main {
	border-radius: var(--border-radius-lg);
	overflow: hidden;
}
.main.fullscreen {
	border-radius: 0;
}

See examples/shadertoy-server/ for complete implementation.

Common Mistakes to Avoid

  1. Handlers after connect() - Register ALL handlers BEFORE calling app.connect()
  2. Missing single-file bundling - Must use vite-plugin-singlefile
  3. Forgetting resource registration - Both tool AND resource must be registered
  4. Missing resourceUri link - Tool must have _meta.ui.resourceUri
  5. Ignoring safe area insets - Always handle ctx.safeAreaInsets
  6. No text fallback - Always provide content array for non-UI hosts
  7. Hardcoded styles - Use host CSS variables for theme integration
  8. No streaming for large inputs - Use ontoolinputpartial to show progress during generation

Testing

Using basic-host

Test MCP Apps locally with the basic-host example:

bash
# Terminal 1: Build and run your server
npm run build && npm run serve

# Terminal 2: Run basic-host (from cloned repo)
cd /tmp/mcp-ext-apps/examples/basic-host
npm install
SERVERS='["http://localhost:3001/mcp"]' npm run start
# Open http://localhost:8080

Configure SERVERS with a JSON array of your server URLs (default: http://localhost:3001/mcp).

Debug with sendLog

Send debug logs to the host application (rather than just the iframe's dev console):

typescript
await app.sendLog({ level: 'info', data: 'Debug message' })
await app.sendLog({ level: 'error', data: { error: err.message } })

Frequently asked questions

What does the Create Mcp App AI skill do?

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.

Why use Create Mcp App on TypingMind?

Because you install it once and use it with any model. Create Mcp App is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Create Mcp App in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tldraw/tldraw/tree/main/apps/mcp-app/.claude/skills/create-mcp-app. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Create Mcp App?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Create Mcp App?

As many as you like. As long as a model supports skills, you can use Create Mcp App with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Create Mcp App AI skill free?

It is published on GitHub by tldraw. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇