mcp-use

Из публичных источников

Фуллстек-фреймворк MCP для разработки MCP-приложений для ChatGPT / Claude и MCP-серверов для AI-агентов.

Машинный перевод · Показать оригинал

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

MCP-серверКатегория: MCP-серверы · SDK и фреймворкиOpen sourceданные проверены 15 окт. 2026 г.

Обзор

  • agent-plugins
  • agentic-framework
  • ai
  • apps-sdk
  • chatgpt
  • claude-code
  • claude-connectors
  • llms
  • mcp
  • mcp-apps

Установка

Команды только показываются, маркетплейс их не выполняет. Сверяйтесь с официальной документацией.
  • Официальный сайтИз публичных источниковиз метаданных каталога
    manufact.com/ ↗
  • Сборка из исходниковИз публичных источниковиз метаданных каталога

    Сборка из исходников: проверенного рецепта сборки нет — следуйте инструкциям репозитория.

    github.com/mcp-use/mcp-use ↗

Совместимость

«Неизвестно» значит, что доказательств не найдено, а не что продукт несовместим.
ПлатформаСтатусАрхитектураДоказательствоУверенность
Claude (web & desktop)Неизвестно———
Claude CodeНеизвестно———
CursorНеизвестно———
VS CodeНеизвестно———
WindsurfНеизвестно———
ChatGPTНеизвестно———

Релизы

проверено 29 окт. 2026 г.
v20.3.27Последний29 окт. 2026 г.Официальный источник ↗

Файлы версии 20.3.27

К релизу не приложены файлы.

История релизов

Профиль качества

алгоритм quality-v1.0 · оценено 15 окт. 2026 г.
Оценка качества98
Оценка риска0
Уверенность 1.00
Оценка качества и оценка риска — разные показатели. Высокое качество не гарантирует безопасность.

Составляющие оценки

Поддержка · 2020
last activity 0 days ago
Документация · 1515
README 16710 chars, description present
Готовность к использованию · 1515
install instructions: yes; releases: yes
Метаданные · 1010
4/4 of description, homepage, license, topics
Релизы · 1010
10 release(s), latest 0 days ago
Точность категории · 108
classifier confidence 0.8
Популярность · 1010
10770 stars (log-dampened, 10k = max)
Ясность лицензии · 55
SPDX MIT
Сообщество · 55
issues enabled, 1506 forks

Лицензия

MIT
Лицензия известнапо данным хостинга репозитория

Это статус политики каталога, а не юридическое заключение.

Источники

github.com/mcp-use/mcp-useОсновной★ 10 770 звёздактивность 15 окт. 2026 г.Основной репозиторий · Уверенность 1.00

Отзывы

Войдите, чтобы написать отзыв

Отзывов пока нет.

Альтернативы

skybridgeПохожий
Skybridge — это full-stack фреймворк на TypeScript для MCP Apps и ChatGPT Apps. Типобезопасный. На основе React. Не привязан к платформе.MIT · MCP-серверы
gpt-researcherПохожий
Автономный агент, который проводит глубокое исследование любых данных с помощью любых провайдеров LLMApache-2.0 · MCP-серверы
zotero-mcpПохожий
Zotero MCP: связывает вашу исследовательскую библиотеку Zotero с Claude и другими ИИ-ассистентами через Model Context Protocol для обсуждения статей, получения кратких изложений, анализа цитирования и многого другого.MIT · MCP-серверы
google_workspace_mcpПохожий
Управление Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search и Drive с помощью ИИ — комплексный MCP-сервер и CLI-инструмент для Google WorkspaceMIT · MCP-серверы
CloudBase-AI-ToolkitПохожий
Бэкенд для ИИ-агентов программирования на CloudBase — база данных, аутентификация, функции через Plugin, Skills и MCP.MIT · MCP-серверы
anythingmcpПохожий
Самостоятельно размещаемый MCP-шлюз с открытым исходным кодом: превращает любой REST/OpenAPI, SOAP, GraphQL, OData или SQL API в MCP-инструменты для Claude, ChatGPT и Copilot. 474 коннектора, включая SAP S/4HANA и Business One, ERP и системы электронной коммерции.AGPL-3.0 · MCP-серверы

README

Из mcp-use/mcp-use · лицензия MIT · загружено 29 окт. 2026 г.

[!NOTE] Migrating from v1? Give it to your agent:

Migrate this mcp-use project to v2 following
https://docs.mcp-use.com/v2/typescript/server/migration

Read the migration guide →

Get started

Start with your agent

Build an MCP server: https://mcp-use.com/prompt.md

Read the prompt →

Start with code

npx -y create-mcp-use-app@latest

Run npm run dev in the generated project · open http://localhost:3000/mcp/inspector

TS Docs

Everything you need to ship MCP

Quickstart

The scaffold gives you the server, TypeScript configuration, development scripts, Inspector, and a React view pipeline. Start it once and the MCP endpoint also serves a client-ready landing page with its connection URL and setup instructions.

Replace its index.ts with a view-bound tool like this:

import { MCPServer } from "mcp-use";
import { z } from "zod";

const server = new MCPServer({
  name: "weather-app",
  title: "Weather App",
  version: "1.0.0",
});

const weatherInput = z.object({
  city: z.string().describe("City to look up"),
});

const weatherOutput = z.object({
  city: z.string(),
  temperature: z.number(),
  conditions: z.string(),
});

export const getWeather = server.tool(
  {
    name: "get-weather",
    title: "Get weather",
    description: "Get the current weather for a city",
    inputSchema: weatherInput,
    outputSchema: weatherOutput,
    view: { name: "weather-card" },
    annotations: {
      readOnlyHint: true,
      destructiveHint: false,
      openWorldHint: true,
    },
  },
  async ({ city }) => {
    const weather = {
      city,
      temperature: 22,
      conditions: "Sunny",
    };

    return {
      content: [
        {
          type: "text",
          text: `Weather in ${city}: ${weather.conditions}, ${weather.temperature}°C`,
        },
      ],
      structuredContent: weather,
    };
  },
);

export default server;

Explore MCP server tools →

Add Views to your tools

Create views/weather-card/view.tsx. The directory name matches view.name on the tool:

import { useCallTool, useToolContext } from "mcp-use/react";

export default function WeatherCard() {
  const { status, toolOutput, toolInput } =
    useToolContext<"get-weather">();
  const refresh = useCallTool("get-weather");

  if (status === "pending") {
    return <p>Checking the weather in {toolInput?.city ?? "your city"}…</p>;
  }
  if (status === "error") return <p>Could not load the weather.</p>;

  const weather = refresh.data?.structuredContent ?? toolOutput;

  return (
    <main style={{ padding: 24 }}>
      <h2>{weather.city}</h2>
      <p>
        {weather.temperature}°C · {weather.conditions}
      </p>
      <button
        disabled={refresh.isPending}
        onClick={() => void refresh.callTool({ city: weather.city })}
      >
        {refresh.isPending ? "Refreshing…" : "Refresh"}
      </button>
      {refresh.error && <p>{refresh.error.message}</p>}
    </main>
  );
}

Build your first MCP App →

Create ChatGPT Plugin Extensions

Build ChatGPT Plugin Extensions with interactive Views that users can open alongside their conversation. Use useModelContext to let them add content from a View to the conversation, such as a book to discuss or analytics to explore.

import { useModelContext } from "mcp-use/react";

export default function AddBook() {
  const { add, pending, error } = useModelContext();

  async function shareBook() {
    try {
      await add("selected-book", {
        type: "text",
        title: "The Great Gatsby",
        text: "Selected book: The Great Gatsby by F. Scott Fitzgerald",
      });
    } catch (error) {
      console.error("Could not share the book", error);
    }
  }

  return (
    <>
      <button disabled={pending} onClick={shareBook}>
        {pending ? "Adding…" : "Add book to chat"}
      </button>
      {error && <p role="alert">{error.message}</p>}
    </>
  );
}

Little Bookshop

https://github.com/user-attachments/assets/2f9b56c1-f149-430e-b5b6-a258c08491e6

Manufact Analytics

https://github.com/user-attachments/assets/e488c66e-8f65-4930-8e08-711bdf12ec6e

Explore ChatGPT Plugin Extensions →

Build

Create the production build:

npm run build

Inspect

Start development mode to serve the MCP endpoint at http://localhost:3000/mcp. The Inspector is automatically available at http://localhost:3000/mcp/inspector:

npm run dev

Start a tunnel from the Inspector UI or run mcp-use dev --tunnel to get a public URL for your local MCP server and test it with ChatGPT and Claude before deployment. Learn more about tunneling →

Inspect the same server headlessly from the terminal, invoke representative tools, and capture a View screenshot:

npm install --save-dev @mcp-use/client
npx mcp-use client connect local http://localhost:3000/mcp
npx mcp-use client local tools list
npx mcp-use client local tools call get-weather city=Tokyo
npx mcp-use screenshot \
  --server local \
  --tool get-weather \
  city=Tokyo \
  --output weather-card.png

Deploy

Ship to Manufact and get observability, analytics, evals, submission readiness, and Git-based preview environments for free.

npm run deploy

Prefer to run it yourself? Follow the self-hosting guide →.

How mcp-use compares

mcp-use builds on the official TypeScript SDK v2 and adds first-class Views, typed tool-to-UI contracts, an optimized stateless runtime, the Inspector, screenshot verification, agent-first CLI workflows, and deployment.

block-beta
  columns 7

  metric["Metric"] mcp["mcp-use v2"] fastmcp["FastMCP TS"] official["Official SDK v2*"] xmcp["xmcp"] skybridge["Skybridge"] handler["mcp-handler"]

  speed["Speed"] speedMcp["10,982 ops/s"] speedFast["6,628 ops/s"] speedOfficial["8,050 ops/s"] speedXmcp["6,585 ops/s"] speedSkybridge["8,116 ops/s"] speedHandler["6,324 ops/s"]
  install["MCP App<br/>dev stack"] installMcp["74.4 MiB"] installFast["122.5 MiB"] installOfficial["99.0 MiB"] installXmcp["121.9 MiB"] installSkybridge["137.5 MiB"] installHandler["388.0 MiB"]
  packages["Installed<br/>packages"] packagesMcp["51"] packagesFast["180"] packagesOfficial["119"] packagesXmcp["171"] packagesSkybridge["300"] packagesHandler["130"]
  views["Views"] viewsMcp["✅"] viewsFast["✅"] viewsOfficial["◐ Extension"] viewsXmcp["✅"] viewsSkybridge["✅"] viewsHandler["❌"]
  nativeViews["Native Views<br/>on MCP 2026"] nativeViewsMcp["✅"] nativeViewsFast["✅"] nativeViewsOfficial["❌"] nativeViewsXmcp["❌"] nativeViewsSkybridge["❌"] nativeViewsHandler["❌"]
  oauth["One-line<br/>OAuth adapters"] oauthMcp["✅"] oauthFast["◐ Provider/proxy"] oauthOfficial["◐ Primitives"] oauthXmcp["✅"] oauthSkybridge["✅"] oauthHandler["❌"]
  protocol["MCP 2026<br/>protocol"] protocolMcp["✅"] protocolFast["✅"] protocolOfficial["✅"] protocolXmcp["❌"] protocolSkybridge["❌"] protocolHandler["❌"]
  screenshot["Built-in View<br/>screenshot CLI"] screenshotMcp["✅"] screenshotFast["❌"] screenshotOfficial["❌"] screenshotXmcp["❌"] screenshotSkybridge["❌"] screenshotHandler["❌"]
  tunnel["Built-in<br/>tunneling"] tunnelMcp["✅"] tunnelFast["❌"] tunnelOfficial["❌"] tunnelXmcp["❌"] tunnelSkybridge["✅"] tunnelHandler["❌"]
  inspector["Built-in<br/>Inspector"] inspectorMcp["✅"] inspectorFast["✅"] inspectorOfficial["❌"] inspectorXmcp["❌"] inspectorSkybridge["◐ Limited"] inspectorHandler["❌"]

  classDef metricLabel fill:#6e76811a,font-weight:bold
  classDef brand fill:#2ea04333,stroke:#2da44e,stroke-width:3px,font-weight:bold
  classDef header fill:#6e76811a,font-weight:bold
  classDef value fill:#6e76810f,stroke-width:1px
  classDef leader fill:#2ea0432e,stroke:#2da44e,stroke-width:2px,font-weight:bold
  classDef partial fill:#bb80092e,stroke:#bf8700,stroke-width:2px,font-weight:bold
  classDef unavailable fill:#6e76810f,opacity:0.72

  class metric,speed,install,packages,views,nativeViews,oauth,protocol,screenshot,tunnel,inspector metricLabel
  class mcp brand
  class fastmcp,official,xmcp,skybridge,handler header
  class speedFast,speedOfficial,speedXmcp,speedSkybridge,speedHandler,installFast,installOfficial,installXmcp,installSkybridge,installHandler,packagesFast,packagesOfficial,packagesXmcp,packagesSkybridge,packagesHandler value
  class speedMcp,installMcp,packagesMcp,viewsMcp,viewsFast,viewsXmcp,viewsSkybridge,nativeViewsMcp,nativeViewsFast,oauthMcp,oauthXmcp,oauthSkybridge,protocolMcp,protocolFast,protocolOfficial,screenshotMcp,tunnelMcp,tunnelSkybridge,inspectorMcp,inspectorFast leader
  class oauthFast,viewsOfficial,oauthOfficial,inspectorSkybridge partial
  class viewsHandler,nativeViewsOfficial,nativeViewsXmcp,nativeViewsSkybridge,nativeViewsHandler,oauthHandler,protocolXmcp,protocolSkybridge,protocolHandler,screenshotFast,screenshotOfficial,screenshotXmcp,screenshotSkybridge,screenshotHandler,tunnelFast,tunnelOfficial,tunnelXmcp,tunnelHandler,inspectorOfficial,inspectorXmcp,inspectorHandler unavailable

* Includes @modelcontextprotocol/ext-apps, Vite, and zod for an MCP Apps-capable stack.

Install rows compare custom React MCP App development stacks. FastMCP therefore includes the Apps extension, React, Vite React plugin, Vite, TypeScript, and zod rather than only its narrower server-side component workflow. Size is actual node_modules disk usage after a normal npm install, including required peer dependencies.

Read the detailed benchmark report →

Examples

Remix a complete MCP App, inspect the source, or deploy it as a starting point:

PreviewAppWhat it demonstrates
Chart BuilderStructured data rendered as interactive charts · Open demo
Diagram BuilderCreate and edit diagrams through MCP tools · Open demo
Maps ExplorerSearch, detail tools, and an interactive map view · Open demo

Browse all TypeScript examples →

Ecosystem

PackageUse it for
mcp-useTypeScript v2 server framework, React views, and CLI
@mcp-use/clientConnect to MCP servers from Node.js, browsers, React, and sandboxes
@mcp-use/agentBuild model-powered agents on top of MCP clients
@mcp-use/inspectorInspect and debug MCP servers and apps
@mcp-use/tunnelExpose local HTTP, WebSocket, and MCP servers through the managed relay
create-mcp-use-appScaffold servers and interactive apps
mcp-use for PythonBuild Python MCP servers, clients, and agents

Protocol conformance

Security and community

Contributors

Built by Pietro, Luigi, Enrico, and the mcp-use community.

Открыть репозиторий ↗