add-app-tool — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited add-app-tool (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
App tools are rarely the right choice. Reach for one only when all of the following hold:
format() text fallback you have to maintain anyway.App tools cost more than standard tools: an iframe + CSP setup, app.ontoolresult / callServerTool plumbing, host-context wiring (theme, fonts, styles), and a format() text path that has to be content-complete because most clients see only that. Two surfaces to keep in sync, two failure modes per change.
Default to add-tool. This skill is the how-to once that bar is cleared — the "whether to" decision belongs in design-mcp-server.
MCP Apps extend the standard tool pattern with an interactive HTML UI rendered in a sandboxed iframe by the host. Each MCP App consists of two definitions:
.app-tool.ts) — uses appTool() builder, declares resourceUri pointing to the UI resource.app-resource.ts) — uses appResource() builder, serves the bundled HTMLBoth builders are exported from @cyanheads/mcp-ts-core. They handle _meta.ui.resourceUri, the compat key (ui/resourceUri), and the correct MIME type (text/html;profile=mcp-app) automatically.
For the full API, Context interface, and error codes, read the framework's CLAUDE.md/AGENTS.md (loaded at session start).
add-tool instead. Then gather the tool's name, purpose, input/output shape, and what the UI should display from the user's request — ask only if genuinely absentui://{{tool-name}}/app.htmlsrc/mcp-server/tools/definitions/{{tool-name}}.app-tool.tssrc/mcp-server/resources/definitions/{{tool-name}}-ui.app-resource.tscreateApp() arrays (directly in src/index.ts for fresh scaffolds, or via barrels if the repo already has them)_meta.ui and cross-checks tool/resource pairingbun run rebuild && bun run start:stdio (or start:http)/**
* @fileoverview {{TOOL_DESCRIPTION}}
* @module mcp-server/tools/definitions/{{TOOL_NAME}}.app-tool
*/
import { appTool, z } from '@cyanheads/mcp-ts-core';
const UI_RESOURCE_URI = 'ui://{{tool-name}}/app.html';
export const {{TOOL_EXPORT}} = appTool('{{tool_name}}', {
resourceUri: UI_RESOURCE_URI,
title: '{{TOOL_TITLE}}',
description: '{{TOOL_DESCRIPTION}}',
annotations: { readOnlyHint: true },
input: z.object({
// All fields need .describe(). Only JSON-Schema-serializable Zod types allowed.
}),
output: z.object({
// All fields need .describe(). Only JSON-Schema-serializable Zod types allowed.
}),
// auth: ['tool:{{tool_name}}:read'],
async handler(input, ctx) {
ctx.log.info('Processing', { /* relevant input fields */ });
return { /* output */ };
},
// format() serves dual purpose for app tools:
// 1. First text block: JSON for the UI (app.ontoolresult parses it)
// 2. Subsequent blocks: human-readable, content-complete fallback for non-app hosts and LLM context
format(result) {
return [
{ type: 'text', text: JSON.stringify(result) },
{ type: 'text', text: '/* human-readable summary with all LLM-needed fields */' },
];
},
});/**
* @fileoverview UI resource for {{TOOL_NAME}}.
* @module mcp-server/resources/definitions/{{TOOL_NAME}}-ui.app-resource
*/
import { appResource, z } from '@cyanheads/mcp-ts-core';
const ParamsSchema = z.object({}).describe('No parameters. Returns the static HTML app.');
const APP_HTML = `<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>{{TOOL_TITLE}}</title>
<style>/* your styles */</style>
</head>
<body>
<!-- your UI markup -->
<script type="module">
// PROTOTYPING ONLY — replace before shipping. Bundle via Vite +
// vite-plugin-singlefile or inline the SDK. Live CDN imports require
// CSP whitelisting, add supply-chain risk, and break offline use.
// See UI Notes below.
import {
App,
applyDocumentTheme,
applyHostFonts,
applyHostStyleVariables,
} from "https://unpkg.com/@modelcontextprotocol/ext-apps@1/app-with-deps";
const app = new App({ name: "{{TOOL_TITLE}}", version: "1.0.0" });
function applyHostContext(hostContext) {
if (hostContext?.theme) {
applyDocumentTheme(hostContext.theme);
}
if (hostContext?.styles?.variables) {
applyHostStyleVariables(hostContext.styles.variables);
}
if (hostContext?.styles?.css?.fonts) {
applyHostFonts(hostContext.styles.css.fonts);
}
}
// Receive initial tool result from the host
app.ontoolresult = (result) => {
const text = result.content?.find(c => c.type === "text")?.text;
if (!text) return;
const data = JSON.parse(text);
// render data into the DOM
};
app.onhostcontextchanged = applyHostContext;
// Proactively call tools from the UI
document.getElementById("action-btn").addEventListener("click", async () => {
const result = await app.callServerTool({
name: "{{tool_name}}",
arguments: { /* input */ },
});
// handle result
});
app.connect().then(() => {
const hostContext = app.getHostContext();
if (hostContext) applyHostContext(hostContext);
});
</script>
</body>
</html>`;
export const {{RESOURCE_EXPORT}} = appResource('ui://{{tool-name}}/app.html', {
name: '{{tool-name}}-ui',
title: '{{TOOL_TITLE}} UI',
description: 'Interactive HTML app for {{tool_name}}.',
params: ParamsSchema,
// auth: ['resource:{{tool-name}}-ui:read'],
_meta: {
ui: {
csp: { resourceDomains: ['https://unpkg.com'] },
},
},
handler(_params, ctx) {
ctx.log.debug('Serving app UI.', { resourceUri: ctx.uri?.href });
return APP_HTML;
},
list: () => ({
resources: [
{
uri: 'ui://{{tool-name}}/app.html',
name: '{{TOOL_TITLE}}',
description: 'Interactive UI for {{tool_name}}.',
},
],
}),
});vite-plugin-singlefile or inline the SDK. Live CDN imports in a ui:// resource are a CSP footgun (every domain has to be whitelisted on _meta.ui.csp.resourceDomains), a supply-chain footgun (third-party JS executes inside the host's iframe), and a runtime footgun (every render needs network). The unpkg line in the template is for prototyping only.appResource(), put _meta.ui.csp.resourceDomains on the definition; the builder mirrors it into returned resources/read content items. With plain resource(), attach _meta.ui yourself in format().applyDocumentTheme(hostContext.theme) — sets color-scheme and a data-theme attribute on <html>applyHostStyleVariables(hostContext.styles.variables) — installs host CSS custom properties on :root (host decides the names, e.g. --mcp-color-bg-primary)applyHostFonts(hostContext.styles.css.fonts) — installs @font-face rules for the host's font stackAuthor CSS to consume these via var(--mcp-color-bg-primary, /* fallback */ #fff). Don't hardcode brand colors that fight the host.
app.connect() is async — host context arrives a frame or two after first paint. Without a baseline, the UI flashes unstyled or wrong-themed on light hosts. Ship a prefers-color-scheme-aware default so the first frame is sensible: :root { color-scheme: light dark; --bg: #fff; --fg: #111; }
@media (prefers-color-scheme: dark) { :root { --bg: #0c0d12; --fg: #ededef; } }
body { background: var(--bg); color: var(--fg); }Host vars override these once onhostcontextchanged fires.
text content block is typically JSON that the UI parses via ontoolresult. Additional blocks are the human-readable fallback that non-app hosts and LLMs consume — they must render every field the LLM needs to reason about. JSON-only payloads leave model-visible context blind.appResource() already preserves raw HTML for the default app MIME type and mirrors definition _meta.ui into content items. Add a custom format() only when you need extra per-read metadata or non-default content shaping.// src/index.ts (fresh scaffold default)
import { createApp } from '@cyanheads/mcp-ts-core';
import { {{TOOL_EXPORT}} } from './mcp-server/tools/definitions/{{tool-name}}.app-tool.js';
import { {{RESOURCE_EXPORT}} } from './mcp-server/resources/definitions/{{tool-name}}-ui.app-resource.js';
await createApp({
tools: [{{TOOL_EXPORT}}],
resources: [{{RESOURCE_EXPORT}}],
prompts: [/* existing prompts */],
});If the repo already uses definitions/index.ts barrels, update those instead of changing the registration pattern.
src/mcp-server/tools/definitions/{{tool-name}}.app-tool.ts using appTool()src/mcp-server/resources/definitions/{{tool-name}}-ui.app-resource.ts using appResource()resourceUri matches between tool and resource (ui://{{tool-name}}/app.html).describe(), only JSON-Schema-serializable typesformat() first block is JSON.stringify(result) — the full output object for the UI to parse via app.ontoolresult. Subsequent blocks are human-readable, content-complete fallback for non-app hosts and LLMs_meta.ui.csp.resourceDomains lists every external domain loaded by the UIapp.ontoolresultapp.onhostcontextchangedlist callback returning at least one URI so resource-aware clients can discover itcreateApp() arrays (directly or via barrels)createMockContext(), or add-test skill run to scaffold the test filebun run devcheck passes (linter validates _meta.ui and tool/resource pairing)bun run rebuild && bun run start:stdio (or start:http)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.