Token导航 LogoToken导航

Agent Skill · 研究检索

build-mcp-app(构建 MCP 应用)

build-mcp-app 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

build-mcp-app 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 4,504。

总安装 31,824周安装 1,293GitHub Stars 18,206下载 10,192核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:build-mcp-app(构建 MCP 应用)
来源仓库:https://github.com/anthropics/claude-plugins-official
仓库路径:skills/build-mcp-app
安装命令:
npx skills add https://github.com/anthropics/claude-plugins-official --skill build-mcp-app
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/anthropics/claude-plugins-official --skill build-mcp-app

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

在标准 MCP 服务器基础上增加交互式 UI 组件层。支持 Claude 与 ChatGPT 等平台内嵌渲染 widgets。UI 层与底层工具解耦,可独立升级维护。本地开发需通过 Cloudflare tunnel 暴露接口供 Claude 调试。

build-mcp-app 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/build-mcp-app

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/anthropics/claude-plugins-official --skill bui…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

build-mcp-app 怎么安装?

在终端执行 npx skills add https://github.com/anthropics/claude-plugins-official --skill build-mcp-app。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

build-mcp-app 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

build-mcp-app 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

build-mcp-app 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

build-mcp-app 用的人多吗?

公开数据是累计安装 31,824 次,近一周安装 1,293 次,下载 10,192 次,GitHub 18,206 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

build-mcp-app 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 来源仓库有 18,206 星,维护活跃度相对可查。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
build-mcp-app

构建 MCP 应用 · 本页

31,82418,206调用外部服务未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Build an MCP App (Interactive UI Widgets)

An MCP app is a standard MCP server that also serves UI resources — interactive components rendered inline in the chat surface. Build once, runs in Claude *and* ChatGPT and any other host that implements the apps surface.

The UI layer is additive. Under the hood it's still tools, resources, and the same wire protocol. If you haven't built a plain MCP server before, the build-mcp-server skill covers the base layer. This skill adds widgets on top.

Testing in Claude: Add the server as a custom connector in claude.ai (via a Cloudflare tunnel for local dev) — this exercises the real iframe sandbox and hostContext. See https://claude.com/docs/connectors/building/testing.

Claude host specifics

_meta.ui.* keyWhereEffect
resourceUritoolWhich ui:// resource the host renders for this tool's results.
visibility: ["app"]toolHide a widget-only helper tool (e.g. geometry/image fetcher called via callServerTool) from Claude's tool list.
prefersBorder: falseresourceDrop the host's outer card border (mobile).
csp.{connectDomains, resourceDomains, baseUriDomains}resourceDeclare external origins; default is block-all. frameDomains is currently restricted in Claude.
  • hostContext.safeAreaInsets: {top, right, bottom, left} (px) — honor these for notches and the composer overlay.
  • Directory submission requires OAuth or authless (none) — static bearer is private-deploy only and blocks listing — plus tool annotations and 3–5 PNG screenshots; see references/directory-checklist.md.

When a widget beats plain text

Don't add UI for its own sake — most tools are fine returning text or JSON. Add a widget when one of these is true:

SignalWidget type
Tool needs structured input Claude can't reliably inferForm
User must pick from a list Claude can't rank (files, contacts, records)Picker / table
Destructive or billable action needs explicit confirmationConfirm dialog
Output is spatial or visual (charts, maps, diffs, previews)Display widget
Long-running job the user wants to watchProgress / live status

If none apply, skip the widget. Text is faster to build and faster for the user.


Widgets vs Elicitation — route correctly

Before building a widget, check if elicitation covers it. Elicitation is spec-native, zero UI code, works in any compliant host.

NeedElicitationWidget
Confirm yes/no✅overkill
Pick from short enum✅overkill
Fill a flat form (name, email, date)✅overkill
Pick from a large/searchable list❌ (no scroll/search)✅
Visual preview before choosing❌✅
Chart / map / diff view❌✅
Live-updating progress❌✅

If elicitation covers it, use it. See ../build-mcp-server/references/elicitation.md.


Architecture: two deployment shapes

Remote MCP app (most common)

Hosted streamable-HTTP server. Widget templates are served as resources; tool results reference them. The host fetches the resource, renders it in an iframe sandbox, and brokers messages between the widget and Claude.

┌──────────┐  tools/call   ┌────────────┐
│  Claude  │─────────────> │ MCP server │
│   host   │<── result ────│  (remote)  │
│          │  + widget ref │            │
│          │               │            │
│          │ resources/read│            │
│          │─────────────> │  widget    │
│ ┌──────┐ │<── template ──│  HTML/JS   │
│ │iframe│ │               └────────────┘
│ │widget│ │
│ └──────┘ │
└──────────┘

MCPB-packaged MCP app (local + UI)

Same widget mechanism, but the server runs locally inside an MCPB bundle. Use this when the widget needs to drive a local application — e.g., a file picker that browses the actual local disk, a dialog that controls a desktop app.

For MCPB packaging mechanics, defer to the build-mcpb skill. Everything below applies to both shapes.


How widgets attach to tools

A widget-enabled tool has two separate registrations:

  1. The tool declares a UI resource via _meta.ui.resourceUri. Its handler returns plain text/JSON — NOT the HTML.
  2. The resource is registered separately and serves the HTML.

When Claude calls the tool, the host sees _meta.ui.resourceUri, fetches that resource, renders it in an iframe, and pipes the tool's return value into the iframe via the ontoolresult event.

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { registerAppTool, registerAppResource, RESOURCE_MIME_TYPE }
  from "@modelcontextprotocol/ext-apps/server";
import { z } from "zod";

const server = new McpServer({ name: "contacts", version: "1.0.0" });

// 1. The tool — returns DATA, declares which UI to show
registerAppTool(server, "pick_contact", {
  description: "Open an interactive contact picker",
  annotations: { title: "Pick Contact", readOnlyHint: true },
  inputSchema: { filter: z.string().optional() },
  _meta: { ui: { resourceUri: "ui://widgets/contact-picker.html" } },
}, async ({ filter }) => {
  const contacts = await db.contacts.search(filter);
  // Plain JSON — the widget receives this via ontoolresult
  return { content: [{ type: "text", text: JSON.stringify(contacts) }] };
});

// 2. The resource — serves the HTML
registerAppResource(
  server,
  "Contact Picker",
  "ui://widgets/contact-picker.html",
  {},
  async () => ({
    contents: [{
      uri: "ui://widgets/contact-picker.html",
      mimeType: RESOURCE_MIME_TYPE,
      text: pickerHtml,  // your HTML string
    }],
  }),
);

The URI scheme ui:// is convention. The mime type MUST be RESOURCE_MIME_TYPE ("text/html;profile=mcp-app") — this is how the host knows to render it as an interactive iframe, not just display the source.


Widget runtime — the App class

Inside the iframe, your script talks to the host via the App class from @modelcontextprotocol/ext-apps. This is a persistent bidirectional connection — the widget stays alive as long as the conversation is active, receiving new tool results and sending user actions.

<script type="module">
  /* ext-apps bundle inlined at build time → globalThis.ExtApps */
  /*__EXT_APPS_BUNDLE__*/
  const { App } = globalThis.ExtApps;

  const app = new App({ name: "ContactPicker", version: "1.0.0" }, {});

  // Set handlers BEFORE connecting
  app.ontoolresult = ({ content }) => {
    const contacts = JSON.parse(content[0].text);
    render(contacts);
  };

  await app.connect();

  // Later, when the user clicks something:
  function onPick(contact) {
    app.sendMessage({
      role: "user",
      content: [{ type: "text", text: `Selected contact: ${contact.id}` }],
    });
  }
</script>

The /*__EXT_APPS_BUNDLE__*/ placeholder gets replaced by the server at startup with the contents of @modelcontextprotocol/ext-apps/app-with-deps — see references/iframe-sandbox.md for why this is necessary and the rewrite snippet. Do not import {App} from "https://esm.sh/..."; the iframe's CSP blocks the transitive dependency fetches and the widget renders blank.

MethodDirectionUse for
app.ontoolresult = fnHost → widgetReceive the tool's return value
app.ontoolinput = fnHost → widgetReceive the tool's input args (what Claude passed)
app.sendMessage({...})Widget → hostInject a message into the conversation
app.updateModelContext({...})Widget → hostUpdate context silently (no visible message)
app.callServerTool({name, arguments})Widget → serverCall another tool on your server
app.openLink({url})Widget → hostOpen a URL in a new tab (sandbox blocks window.open)
app.getHostContext() / app.onhostcontextchangedHost → widgetTheme, host CSS vars, containerDimensions, displayMode, deviceCapabilities
app.requestDisplayMode({mode})Widget → hostAsk for inline / pip / fullscreen
app.downloadFile({name, mimeType, content})Widget → hostHost-mediated download (base64 content)
new App(info, caps, {autoResize: true})—Iframe height tracks rendered content

sendMessage is the typical "user picked something, tell Claude" path. updateModelContext is for state that Claude should know about but shouldn't clutter the chat. openLink is required for any outbound navigation — window.open and <a target="_blank"> are blocked by the sandbox attribute.

What widgets cannot do:

  • Access the host page's DOM, cookies, or storage
  • Make network calls to arbitrary origins (CSP-restricted — route through callServerTool)
  • Open popups or navigate directly — use app.openLink({url})
  • Load remote images reliably — inline as data: URLs server-side

Keep widgets small and single-purpose. A picker picks. A chart displays. Don't build a whole sub-app inside the iframe — split it into multiple tools with focused widgets.


Scaffold: minimal picker widget

Install:

npm install @modelcontextprotocol/sdk @modelcontextprotocol/ext-apps zod express

Server (src/server.ts):

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js";
import { registerAppTool, registerAppResource, RESOURCE_MIME_TYPE }
  from "@modelcontextprotocol/ext-apps/server";
import express from "express";
import { readFileSync } from "node:fs";
import { createRequire } from "node:module";
import { z } from "zod";

const require = createRequire(import.meta.url);
const server = new McpServer({ name: "contact-picker", version: "1.0.0" });

// Inline the ext-apps browser bundle into the widget HTML.
// The iframe CSP blocks CDN script fetches — bundling is mandatory.
const bundle = readFileSync(
  require.resolve("@modelcontextprotocol/ext-apps/app-with-deps"), "utf8",
).replace(/export\{([^}]+)\};?\s*$/, (_, body) =>
  "globalThis.ExtApps={" +
  body.split(",").map((p) => {
    const [local, exported] = p.split(" as ").map((s) => s.trim());
    return `${exported ?? local}:${local}`;
  }).join(",") + "};",
);
const pickerHtml = readFileSync("./widgets/picker.html", "utf8")
  .replace("/*__EXT_APPS_BUNDLE__*/", () => bundle);

registerAppTool(server, "pick_contact", {
  description: "Open an interactive contact picker. User selects one contact.",
  annotations: { title: "Pick Contact", readOnlyHint: true },
  inputSchema: { filter: z.string().optional().describe("Name/email prefix filter") },
  _meta: { ui: { resourceUri: "ui://widgets/picker.html" } },
}, async ({ filter }) => {
  const contacts = await db.contacts.search(filter ?? "");
  return { content: [{ type: "text", text: JSON.stringify(contacts) }] };
});

registerAppResource(server, "Contact Picker", "ui://widgets/picker.html", {},
  async () => ({
    contents: [{ uri: "ui://widgets/picker.html", mimeType: RESOURCE_MIME_TYPE, text: pickerHtml }],
  }),
);

const app = express();
app.use(express.json());
app.post("/mcp", async (req, res) => {
  const transport = new StreamableHTTPServerTransport({ sessionIdGenerator: undefined });
  res.on("close", () => transport.close());
  await server.connect(transport);
  await transport.handleRequest(req, res, req.body);
});
app.listen(process.env.PORT ?? 3000);

For local-only widget apps (driving a desktop app, reading local files), swap the transport to StdioServerTransport and package via the build-mcpb skill.

Widget (widgets/picker.html):

<!doctype html>
<meta charset="utf-8" />
<style>
  body { font: 14px system-ui; margin: 0; }
  ul { list-style: none; padding: 0; margin: 0; max-height: 300px; overflow-y: auto; }
  li { padding: 10px 14px; cursor: pointer; border-bottom: 1px solid #eee; }
  li:hover { background: #f5f5f5; }
  .sub { color: #666; font-size: 12px; }
</style>
<ul id="list"></ul>
<script type="module">
/*__EXT_APPS_BUNDLE__*/
const { App } = globalThis.ExtApps;
(async () => {
  const app = new App({ name: "ContactPicker", version: "1.0.0" }, {});
  const ul = document.getElementById("list");

  app.ontoolresult = ({ content }) => {
    const contacts = JSON.parse(content[0].text);
    ul.innerHTML = "";
    for (const c of contacts) {
      const li = document.createElement("li");
      li.innerHTML = `<div>${c.name}</div><div class="sub">${c.email}</div>`;
      li.addEventListener("click", () => {
        app.sendMessage({
          role: "user",
          content: [{ type: "text", text: `Selected contact: ${c.id} (${c.name})` }],
        });
      });
      ul.append(li);
    }
  };

  await app.connect();
})();
</script>

See references/widget-templates.md for more widget shapes.


Design notes that save you a rewrite

One widget per tool. Resist the urge to build one mega-widget that does everything. One tool → one focused widget → one clear result shape. Claude reasons about these far better.

Tool description must mention the widget. Claude only sees the tool description when deciding what to call. "Opens an interactive picker" in the description is what makes Claude reach for it instead of guessing an ID.

Widgets are optional at runtime. Hosts that don't support the apps surface simply ignore _meta.ui and render the tool's text content normally. Since your tool handler already returns meaningful text/JSON (the widget's data), degradation is automatic — Claude sees the data directly instead of via the widget.

Don't block on widget results for read-only tools. A widget that just *displays* data (chart, preview) shouldn't require a user action to complete. Return the display widget *and* a text summary in the same result so Claude can continue reasoning without waiting.

Layout-fork by item count, not by tool count. If one use case is "show one result in detail" and another is "show many results side-by-side", don't make two tools — make one tool that accepts items[], and let the widget pick a layout: items.length === 1 → detail view, > 1 → carousel. Keeps the server schema simple and lets Claude decide count naturally.

Put Claude's reasoning in the payload. A short note field on each item (why Claude picked it) rendered as a callout on the card gives users the reasoning inline with the choice. Mention this field in the tool description so Claude populates it.

Normalize image shapes server-side. If your data source returns images with wildly varying aspect ratios, rewrite to a predictable variant (e.g. square-bounded) *before* fetching for the data-URL inline. Then give the widget's image container a fixed aspect-ratio + object-fit: contain so everything sits centered.

Follow host theme. app.getHostContext()?.theme (after connect()) plus app.onhostcontextchanged for live updates. Toggle a .dark class on <html>, keep colors in CSS custom props with a :root.dark {} override block, set color-scheme. Disable mix-blend-mode: multiply in dark — it makes images vanish.


Testing

Claude Desktop — current builds still require the command/args config shape (no native "type": "http"). Wrap with mcp-remote and force http-only transport so the SSE probe doesn't swallow widget-capability negotiation:

{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://localhost:3000/mcp",
               "--allow-http", "--transport", "http-only"]
    }
  }
}

Desktop caches UI resources aggressively. After editing widget HTML, fully quit (⌘Q / Alt+F4, not window-close) and relaunch to force a cold resource re-fetch.

Headless JSON-RPC loop — fast iteration without clicking through Desktop:

# test.jsonl — one JSON-RPC message per line
{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"t","version":"0"}}}
{"jsonrpc":"2.0","method":"notifications/initialized"}
{"jsonrpc":"2.0","id":2,"method":"tools/list"}
{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"your_tool","arguments":{...}}}

(cat test.jsonl; sleep 10) | npx mcp-remote http://localhost:3000/mcp --allow-http

The sleep keeps stdin open long enough to collect all responses. Parse the jsonl output with jq or a Python one-liner.

Widget dev loop — avoid the ⌘Q-relaunch cycle entirely by serving the inlined widget HTML at a plain GET route with a fake ExtApps shim that fires ontoolresult from a query param:

app.get("/widget-preview", (_req, res) => {
  const shim = `globalThis.ExtApps={applyHostStyleVariables:()=>{},App:class{
    constructor(){this.h={}} ontoolresult;onhostcontextchanged;
    async connect(){const p=new URLSearchParams(location.search).get("payload");
      if(p)this.ontoolresult?.({content:[{type:"text",text:p}]});}
    getHostContext(){return{theme:"light"}}
    sendMessage(m){console.log("sendMessage",m)} updateModelContext(){}
    callServerTool(){return Promise.resolve({content:[]})} openLink(){} downloadFile(){}
  }};`;
  res.type("html").send(widgetHtml.replace("/*__EXT_APPS_BUNDLE__*/", shim));
});

Open http://localhost:3000/widget-preview?payload={"rows":[...]} in a normal browser tab and iterate with ordinary devtools.

Host fallback — use a host without the apps surface (or MCP Inspector) and confirm the tool's text content degrades gracefully.

CSP debugging — open the iframe's own devtools console. CSP violations are the #1 reason widgets silently fail (blank rectangle, no error in the main console). See references/iframe-sandbox.md.


Reference files

  • references/iframe-sandbox.md — CSP/sandbox constraints, the bundle-inlining pattern, image handling, host theming
  • references/widget-templates.md — reusable HTML scaffolds for picker / confirm / progress / display
  • references/apps-sdk-messages.md — the App class API: widget ↔ host ↔ server messaging, lifecycle & supersession
  • references/payload-budgeting.md — host tool-result size caps, prune-then-truncate, heavy assets via callServerTool
  • references/abuse-protection.md — Anthropic egress CIDRs, tiered rate limiting, trust proxy, response caching
  • references/directory-checklist.md — pre-flight for connector-directory submission

平台分布

Codex

32.37%
按下载量换算3,299

Claude

29.89%
按下载量换算3,046

Cursor

20.11%
按下载量换算2,050

Gemini CLI

8.89%
按下载量换算906

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills