Borrowing it
Nothing to install: this file belongs to digitarald/mcp-apps-playground. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/digitarald/mcp-apps-playground/main/.github/skills/mcp-apps/SKILL.mdgit clone --depth 1 https://github.com/digitarald/mcp-apps-playgroundWrote 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.
[](https://agentmods.dev/skills/digitarald/mcp-apps-playground/mcp-apps)<a href="https://agentmods.dev/skills/digitarald/mcp-apps-playground/mcp-apps"><img src="https://agentmods.dev/badge/skills/digitarald/mcp-apps-playground/mcp-apps/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.
<a href="https://agentmods.dev/skills/digitarald/mcp-apps-playground/mcp-apps"><img src="https://agentmods.dev/badge/skills/digitarald/mcp-apps-playground/mcp-apps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00096 | $0.01898 |
| Opus 5 | $0.00048 | $0.00949 |
| Sonnet 5 | $0.00019 | $0.00380 |
| Haiku 4.5 | $0.00010 | $0.00190 |
Grade A, and why
mcp-apps 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Apps Development
MCP Apps let MCP tools render interactive HTML UIs in chat. The UI runs in a sandboxed iframe and communicates via JSON-RPC postMessage.
External References
- Spec: https://github.com/modelcontextprotocol/ext-apps/blob/main/specification/draft/apps.mdx
- Blog: https://blog.modelcontextprotocol.io/posts/2025-11-21-mcp-apps/
- VS Code impl: https://github.com/microsoft/vscode (search
chatMcpAppModel.ts)
Quick Start
1. Register UI Resource
server.resource(
"my-ui",
"ui://my-server/my-tool", // ui:// scheme required
{ mimeType: "text/html;profile=mcp-app" }, // profile required
async (uri) => ({
contents: [{
uri: uri.href,
mimeType: "text/html;profile=mcp-app", // must match
text: MY_UI_HTML()
}]
})
);
2. Register Tool with UI Link
server.registerTool("my_tool", {
inputSchema: { query: z.string() },
_meta: { ui: { resourceUri: "ui://my-server/my-tool" } }
}, async ({ query }) => ({
content: [{ type: "text", text: `Result: ${query}` }],
structuredContent: { query, result: "..." } // sent to UI
}));
3. UI Template (Static HTML)
export function MY_UI_HTML(): string {
return `<!DOCTYPE html>
<html><body>
<div id="content">Loading...</div>
<script>
const pending = new Map();
let nextId = 1;
function request(method, params) {
const id = nextId++;
return new Promise((resolve, reject) => {
pending.set(id, { resolve, reject });
window.parent.postMessage({ jsonrpc: '2.0', id, method, params }, '*');
});
}
window.addEventListener('message', (e) => {
const msg = e.data;
if (!msg?.jsonrpc) return;
// Handle responses
if (msg.id && pending.has(msg.id)) {
const { resolve, reject } = pending.get(msg.id);
pending.delete(msg.id);
msg.error ? reject(msg.error) : resolve(msg.result);
return;
}
// Handle notifications
if (msg.method === 'ui/notifications/tool-input') {
const { arguments: args } = msg.params;
document.getElementById('content').textContent = JSON.stringify(args);
}
});
// Initialize handshake
request('ui/initialize', { protocolVersion: '2025-11-21' }).then(() => {
window.parent.postMessage({ jsonrpc: '2.0', method: 'ui/notifications/initialized' }, '*');
});
<\/script>
</body></html>`;
}
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 218 lines · 96 tokens per session scan A 5596166b1538
mcp-apps is a skill published in the GitHub repository digitarald/mcp-apps-playground (73 stars, last pushed 7mo ago), licensed MIT. It adds 96 tokens to every session and 1,898 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…