What is mcp-app-create?

A development guide for building MCP Apps: interactive HTML interfaces connected to MCP tools and shown inside MCP-enabled hosts such as Claude Desktop.

Use it to scaffold an MCP App, register its UI resource, connect the interface to tool results, and handle host integration.

It explains how the tool, data, HTML resource, and host fit together, reducing guesswork when adding an interface to an MCP tool.

How OlliMakarova/mcp-metro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OlliMakarova/mcp-metro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/OlliMakarova/mcp-metro/master/.claude/skills/mcp-app-create/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/OlliMakarova/mcp-metro

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/mcp-app-create/github.svg)](https://agentmods.dev/skills/ollimakarova/mcp-metro/mcp-app-create)

Your own site

<a href="https://agentmods.dev/skills/ollimakarova/mcp-metro/mcp-app-create"><img src="https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/mcp-app-create/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ollimakarova/mcp-metro/mcp-app-create"><img src="https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/mcp-app-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,816 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 92% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00077	$0.02816
Opus 5.5	$0.00031	$0.01126
Sonnet 5.5	$0.00015	$0.00563
Haiku 4.5	$0.00008	$0.00282

Measured 2mo ago against content hash 1014c3b1ab92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-app-create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

92% identical to mcp-app-create — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/mcp-app-create/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Preferred pattern: reference the widget via _meta.ui.resourceUri. This "Tool + separate Resource" form — the tool declares _meta.ui.resourceUri and the HTML is registered as its own ui:// resource that the host fetches with resources/read — is the recommended way to ship a widget, and the only one this skill scaffolds. Prefer it over the embedded alternative, where the tool returns the ui:// resource inline in its result content[]. The referenced form lets the host fetch and cache the static shell once, review its _meta.ui (CSP, permissions, domain) before rendering, and know the widget exists before the call — which is what enables app-only tools (visibility: ["app"]) and the "UI" badge / "Launch widget" button in the Agent Tester Inspector. Reserve the embedded form for quick, one-off, fully data-dependent widgets where those benefits don't matter.

Quick Start Decision Tree

Framework Selection

Framework	`@modelcontextprotocol/ext-apps` 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, registerAppResource from @modelcontextprotocol/ext-apps
Add tool registration with _meta.ui.resourceUri
Add resource registration serving bundled HTML

Read the full file on GitHub · 239 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 239 lines · 77 tokens per session scan A 1014c3b1ab92

Subscribe to this mod's changes

mcp-app-create is a skill published in the GitHub repository OlliMakarova/mcp-metro (0 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 2,816 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to mcp-app-create, differing in 10 lines, and is treated as a copy.

Building agents Frontend

mcp-app-create next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-app-createOlliMakarova/mcp-metro	Skill	0	3mo ago	MIT	A	77	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

mcp-metro: Skill for Claude Code