Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Tyler-R-Kendrick/agent-skills --skill mcp-appsgit clone --depth 1 https://github.com/Tyler-R-Kendrick/agent-skillsWrote 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/tyler-r-kendrick/agent-skills/mcp-apps)<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/mcp-apps"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/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/tyler-r-kendrick/agent-skills/mcp-apps"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/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 | $0.00090 | $0.01017 |
| Opus 5.5 | $0.00036 | $0.00407 |
| Sonnet 5.5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Apps
Overview
MCP Apps is an extension to the Model Context Protocol that lets MCP servers return rich, interactive user interfaces instead of plain text. When a tool declares a UI resource, the host renders it in a sandboxed iframe, and users interact with it directly in the conversation. Supported by Claude, VS Code, Goose, and Postman.
How It Works
MCP Server Host (Claude, VS Code)
│ │
│◄── tool call ─────────────────│
│── tool result + ui resource ─►│
│ │── render iframe ──► User
│◄── JSON-RPC messages ────────│◄── user interaction
- A tool declares a
uifield referencing aui://resource - The host calls the tool and receives the result with a UI reference
- The host fetches the UI content and renders it in a sandboxed iframe
- The UI communicates with the host via JSON-RPC over
postMessage
Declaring UI in a Tool
{
"name": "render_dashboard",
"description": "Display an interactive dashboard",
"inputSchema": {
"type": "object",
"properties": {
"data": { "type": "object" }
}
},
"ui": {
"uri": "ui://dashboard",
"title": "Dashboard"
}
}
UI Resource
The server registers a UI resource that returns HTML:
@mcp.resource("ui://dashboard")
def dashboard() -> str:
return """
<!DOCTYPE html>
<html>
<body>
<h1>Dashboard</h1>
<div id="chart"></div>
<script>
// Communicate with the host via JSON-RPC
window.addEventListener('message', (event) => {
const { method, params } = event.data;
if (method === 'initialize') {
renderChart(params.data);
}
});
</script>
</body>
</html>
"""
URI Scheme
MCP Apps use the ui:// URI scheme:
ui://dashboard— predeclared UI template- Only
text/htmlcontent is supported in the initial specification - External URLs, remote DOM, and native widgets are deferred to future versions
What ships with it
11 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.
- AGENTS.md 3.4 KB
- metadata.json 656 B
- README.md 634 B
- rules/_sections.md 1.2 KB
- rules/_template.md 367 B
- rules/mcp-apps-design-for-the-iframe-sandbox-restrictions.md 389 B
- rules/mcp-apps-fall-back-gracefully-to-text-content-if-the-host-does-not.md 398 B
- rules/mcp-apps-keep-ui-self-contained.md 355 B
- rules/mcp-apps-keep-uis-lightweight.md 328 B
- rules/mcp-apps-provide-a-meaningful-title-in-the-ui-declaration-for.md 386 B
- rules/mcp-apps-use-the-json-rpc-postmessage-bridge-for-all-data-exchange.md 407 B
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 · 123 lines · 90 tokens per session scan A 6e682a06bad0
mcp-apps is a skill published in the GitHub repository Tyler-R-Kendrick/agent-skills (13 stars, last pushed 5mo ago), licensed MIT. It adds 90 tokens to every session and 1,017 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
mcp-apps compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-appsTyler-R-Kendrick/agent-skills | Skill | 13 | 5mo ago | MIT | A | 90 | 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 |