
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.
- Installs
- 2.7K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/modelcontextprotocol/ext-apps --skill create-mcp-app- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads create-mcp-app automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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
The tool's _meta.ui.resourceUri references the resource's URI.
Host calls tool → Host renders resource UI → Server returns result → 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:
server.tswithregisterAppToolandregisterAppResourcemain.tsentry point with HTTP and stdio transport setup- Client-side app (e.g.,
src/mcp-app.ts,src/mcp-app.tsx) with lifecycle handlers src/global.csswith global styles and host style variable fallbacksvite.config.tsusingvite-plugin-singlefilepackage.jsonwithnpm runscripts and 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, etc.), lifecycle |
src/server/index.ts | registerAppTool, registerAppResource, helper functions |
src/spec.types.ts | All type definitions: McpUiHostContext, McpUiStyleVariableKey (CSS variable names), McpUiResourceCsp (CSP configuration), etc. |
src/styles.ts | applyDocumentTheme, applyHostStyleVariables, applyHostFonts |
src/react/useApp.tsx | useApp hook for React apps |
Advanced Patterns
See /tmp/mcp-ext-apps/docs/patterns.md for detailed recipes:
- App-only tools —
visibility: ["app"], hiding tools from model - Polling — real-time dashboards, interval management
- Chunked responses — large files, pagination, base64 encoding
- Error handling —
isError, informing model of failures - Binary resources — audio/video/etc via
resources/read, blob field - Network requests — assets, fetch, CSP,
_meta.ui.csp, CORS,_meta.ui.domain - Host context — theme, styling, fonts, safe area insets
- Fullscreen mode —
requestDisplayMode, display mode changes - Model context —
updateModelContext,sendMessage, keeping model informed - View state —
viewUUID, localStorage, state recovery - Visibility-based pause — IntersectionObserver, pausing animations/WebGL
- Streaming input —
ontoolinputpartial, progressive rendering
Reference Host Implementation
/tmp/mcp-ext-apps/examples/basic-host/ shows one way an MCP Apps-capable host could be implemented. Real-world hosts like Claude Desktop are more sophisticated—use basic-host for local testing and protocol understanding, not as a guarantee of host behavior.
Critical Implementation Notes
Adding Dependencies
Always use npm install to add dependencies rather than manually writing version numbers:
npm install @modelcontextprotocol/ext-apps @modelcontextprotocol/client@^2.0.0 @modelcontextprotocol/server@^2.0.0 @modelcontextprotocol/node@^2.0.0 @modelcontextprotocol/express@^2.0.0 zod@^4.2.0 express cors
npm install -D typescript vite vite-plugin-singlefile concurrently cross-env @types/node @types/express @types/cors
ext-apps 2.x requires the split base MCP SDK packages (@modelcontextprotocol/client,
server, node, express) at ^2.0.0; @modelcontextprotocol/core comes in
transitively. Do not add the legacy @modelcontextprotocol/sdk v1 package or
substitute unpublished local packages.
TypeScript Server Execution
Unless the user has specified otherwise, use tsx for running TypeScript server files. For example:
npm install -D tsx
npm pkg set scripts.dev="cross-env NODE_ENV=development concurrently 'cross-env INPUT=mcp-app.html vite build --watch' 'tsx --watch main.ts'"
[!NOTE] The SDK examples use
bunbut generated projects should default totsxfor 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 {}; };
// etc.
// Then connect
await app.connect();
Common Mistakes to Avoid
- No text fallback - Always provide
contentarray for non-UI hosts - Missing CSP configuration - MCP Apps HTML is served as an MCP resource with no same-origin server; ALL network requests—even to
localhost—require a CSP configuration - CSP or CORS config in wrong _meta object -
_meta.ui.cspand_meta.ui.domaingo in thecontents[]objects returned byregisterAppResource()'s read callback, not inregisterAppResource()'s config object - Handlers after app.connect() - Register ALL handlers BEFORE calling
app.connect() - No streaming for large inputs - Use
ontoolinputpartialto show progress during input generation
Testing
Using basic-host
Test MCP Apps locally with the basic-host example:
# 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):
await app.sendLog({ level: "info", data: "Debug message" });
await app.sendLog({ level: "error", data: { error: err.message } });
FAQ
What does the create-mcp-app 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.
How do I install create-mcp-app?
Run npx skills add https://github.com/modelcontextprotocol/ext-apps --skill create-mcp-app in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/create-mcp-app/ (personal) or .claude/skills/create-mcp-app/ (project).
Which AI agents can use create-mcp-app?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is create-mcp-app safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains create-mcp-app?
It is published by modelcontextprotocol in modelcontextprotocol/ext-apps. It has 2,674 recorded installs.
More from modelcontextprotocol/ext-apps
add-app-to-server
modelcontextprotocol/ext-apps
This skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add a view to my MCP tool", "enrich MCP tools with UI", "add interactive UI to existing server", "add MCP Apps to my server", or needs to add interactive UI capabilities to an existing MCP server that already has tools. Provides guidance for analyzing existing tools and adding MCP Apps UI resources.
migrate-oai-app
modelcontextprotocol/ext-apps
This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK. Provides step-by-step migration guidance with API mapping tables.
convert-web-app
modelcontextprotocol/ext-apps
This skill should be used when the user asks to "add MCP App support to my web app", "turn my web app into a hybrid MCP App", "make my web page work as an MCP App too", "wrap my existing UI as an MCP App", "convert iframe embed to MCP App", "turn my SPA into an MCP App", or needs to add MCP App support to an existing web application while keeping it working standalone. Provides guidance for analyzing existing web apps and creating a hybrid web + MCP App with server-side tool and resource registration.
migrate from openai app
modelcontextprotocol/ext-apps
Open the skill to read its SKILL.md instructions.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available