# mcp-use — Fullstack SDK for MCP Servers & Apps

> mcp-use is a fullstack SDK to build MCP servers and MCP apps across Claude/ChatGPT, with inspector + quickstarts. Verified 9952★; pushed 2026-05-14.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

```bash
pip install mcp-use
cat > server.py <<'PY'
from typing import Annotated
from pydantic import Field
from mcp.types import ToolAnnotations
from mcp_use import MCPServer

server = MCPServer(name="Weather Server", version="1.0.0")

@server.tool(
    name="get_weather",
    description="Get current weather information for a location",
    annotations=ToolAnnotations(readOnlyHint=True, openWorldHint=True),
)
async def get_weather(city: Annotated[str, Field(description="City name")]) -> str:
    return f"City: {city} · Temperature: 72°F · Condition: sunny"

server.run(transport="streamable-http", port=8000)
PY
python server.py
# Inspector: http://localhost:8000/inspector
```

## Intro

mcp-use is a fullstack SDK to build MCP servers and MCP apps across Claude/ChatGPT, with inspector + quickstarts. Verified 9952★; pushed 2026-05-14.

**Best for:** Teams who want one codebase to ship MCP tools plus interactive widgets across multiple MCP clients

**Works with:** TypeScript/Node and Python SDKs; includes an inspector UI at `/inspector` (per README examples)

**Setup time:** 8-18 minutes

### Key facts (verified)

- GitHub: 9952 stars · 1285 forks · pushed 2026-05-14.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `server.run(transport='streamable-http', port=8000)`.

## Main

- Use the provided server SDK to define tools with explicit schemas; keep tool names short to avoid client-side limits.

- Treat `/inspector` as your dev loop: validate tool inputs/outputs before wiring the server into Claude/Cursor/ChatGPT.

- If you ship widgets, isolate UI code under a `resources/` folder and keep tool logic separate from presentation.

- Standardize ports/transports per environment (dev vs prod) so clients always know where to connect.

### README (excerpt)

<div align="center">
<div align="center">
  <a href="https://mcp-use.com">
    <picture>
      <source media="(prefers-color-scheme: dark)" srcset="./static/logo_white.svg">
      <source media="(prefers-color-scheme: light)" srcset="./static/logo_black.svg">
      <img alt="mcp use logo" src="./static/logo_black.svg" width="60%" >
    </picture>
  </a>
</div>
&nbsp;

<p align="center">
    <a href="https://mcp-use.com/docs" alt="Documentation">
        <img src="https://img.shields.io/badge/mcp--use-docs-blue?labelColor=white" /></a>
    <a href="https://manufact.com" alt="Website">
        <img src="https://img.shields.io/badge/made by-manufact.com-blue" /></a>
    <a href="https://github.com/mcp-use/mcp-use/blob/main/LICENSE" alt="License">
        <img src="https://img.shields.io/github/license/mcp-use/mcp-use" /></a>
    <a href="https://discord.gg/XkNkSkMz3V" alt="Discord">
        <img src="https://dcbadge.limes.pink/api/server/XkNkSkMz3V?style=flat" /></a>
    <br/>
    <a href="https://mcp-use.com/docs/python" alt="Python docs">
        <img src="https://img.shields.io/badge/python-docs-blue?labelColor=white&logo=python" alt="Badge"></a>
    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Version">
        <img src="https://img.shields.io/pypi/v/mcp_use.svg"/></a>
    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Downloads">
        <img src="https://static.pepy.tech/badge/mcp-use" /></a>
    <br/>
    <a href="https://mcp-use.com/docs/typescript" alt="Typescript Documentation">
        <img src="https://img.shields.io/badge/typescript-docs-blue?labelColor=white&logo=typescript" alt="Badge"></a>
    <a href="https://www.npmjs.com/package/mcp-use" alt="NPM Version">
        <img src="https://img.shields.io/npm/v/mcp-use.svg"/></a>
    <a href="https://www.npmjs.com/package/mcp-use" alt="NPM Downloads">
        <img src="https://img.shields.io/npm/dw/mcp-use.svg"/></a>
    <br/>
</p>
</div>

##  About

  <b>mcp-use</b> is the fullstack MCP framework
  to build MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

- **Build** with mcp-use SDK ([ts](https://www.npmjs.com/package/mcp-use) | [py](https://pypi.org/project/mcp_use/)): MCP Servers and MCP Apps


### Source-backed notes

- README shows a Python quickstart with `pip install mcp-use` and `server.run(transport="streamable-http", port=8000)`.
- README states the inspector is available at `/inspector` for servers started with the built-in runner/listen flow.
- README includes a TypeScript example using `MCPServer` and `server.listen(3000)` with an inspector URL.

### FAQ

- **Do I need TypeScript to use it?**: No—README includes Python quickstarts as well; pick one stack per project.
- **Where is the inspector?**: README examples show `/inspector` on the server port for local debugging.
- **What should I deploy to production?**: Deploy the MCP server endpoint; keep inspector access restricted to trusted environments.

## Source & Thanks

> Created by [mcp-use](https://github.com/mcp-use). Licensed under MIT.
>
> [mcp-use/mcp-use](https://github.com/mcp-use/mcp-use) — ⭐ 9952

Thanks to the upstream maintainers and contributors for publishing this work under an open license.

---

<!-- ZH -->

## Quick Use

```bash
pip install mcp-use
cat > server.py <<'PY'
from typing import Annotated
from pydantic import Field
from mcp.types import ToolAnnotations
from mcp_use import MCPServer

server = MCPServer(name="Weather Server", version="1.0.0")

@server.tool(
    name="get_weather",
    description="Get current weather information for a location",
    annotations=ToolAnnotations(readOnlyHint=True, openWorldHint=True),
)
async def get_weather(city: Annotated[str, Field(description="City name")]) -> str:
    return f"City: {city} · Temperature: 72°F · Condition: sunny"

server.run(transport="streamable-http", port=8000)
PY
python server.py
# Inspector: http://localhost:8000/inspector
```

## Intro

mcp-use 提供 MCP Server 与交互式 MCP App 的全栈 SDK（TS+Python），并配套 Inspector/Quickstart；已验证 9952★，更新于 2026-05-14。

**Best for:** 希望同一套代码同时交付 MCP 工具与交互式组件，并兼容多 MCP 客户端的团队

**Works with:** TypeScript/Node 与 Python SDK；README 示例包含 `/inspector` 调试入口

**Setup time:** 8-18 minutes

### Key facts (verified)

- GitHub：9952 stars · 1285 forks；最近更新 2026-05-14。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口：`server.run(transport='streamable-http', port=8000)`。

## Main

- 用 SDK 明确声明工具与 schema；同时注意工具名长度，避免触发部分客户端的名称限制。

- 把 `/inspector` 当作开发闭环：先验证输入/输出，再接入 Claude/Cursor/ChatGPT 等客户端。

- 如果要做 widget，把 UI 代码放到 `resources/` 一类目录，工具逻辑与展示解耦。

- 在 dev/prod 统一端口与 transport 选择，减少不同客户端连接差异造成的排障成本。

### README (excerpt)

<div align="center">
<div align="center">
  <a href="https://mcp-use.com">
    <picture>
      <source media="(prefers-color-scheme: dark)" srcset="./static/logo_white.svg">
      <source media="(prefers-color-scheme: light)" srcset="./static/logo_black.svg">
      <img alt="mcp use logo" src="./static/logo_black.svg" width="60%" >
    </picture>
  </a>
</div>
&nbsp;

<p align="center">
    <a href="https://mcp-use.com/docs" alt="Documentation">
        <img src="https://img.shields.io/badge/mcp--use-docs-blue?labelColor=white" /></a>
    <a href="https://manufact.com" alt="Website">
        <img src="https://img.shields.io/badge/made by-manufact.com-blue" /></a>
    <a href="https://github.com/mcp-use/mcp-use/blob/main/LICENSE" alt="License">
        <img src="https://img.shields.io/github/license/mcp-use/mcp-use" /></a>
    <a href="https://discord.gg/XkNkSkMz3V" alt="Discord">
        <img src="https://dcbadge.limes.pink/api/server/XkNkSkMz3V?style=flat" /></a>
    <br/>
    <a href="https://mcp-use.com/docs/python" alt="Python docs">
        <img src="https://img.shields.io/badge/python-docs-blue?labelColor=white&logo=python" alt="Badge"></a>
    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Version">
        <img src="https://img.shields.io/pypi/v/mcp_use.svg"/></a>
    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Downloads">
        <img src="https://static.pepy.tech/badge/mcp-use" /></a>
    <br/>
    <a href="https://mcp-use.com/docs/typescript" alt="Typescript Documentation">
        <img src="https://img.shields.io/badge/typescript-docs-blue?labelColor=white&logo=typescript" alt="Badge"></a>
    <a href="https://www.npmjs.com/package/mcp-use" alt="NPM Version">
        <img src="https://img.shields.io/npm/v/mcp-use.svg"/></a>
    <a href="https://www.npmjs.com/package/mcp-use" alt="NPM Downloads">
        <img src="https://img.shields.io/npm/dw/mcp-use.svg"/></a>
    <br/>
</p>
</div>

##  About

  <b>mcp-use</b> is the fullstack MCP framework
  to build MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

- **Build** with mcp-use SDK ([ts](https://www.npmjs.com/package/mcp-use) | [py](https://pypi.org/project/mcp_use/)): MCP Servers and MCP Apps


### Source-backed notes

- README 的 Python quickstart 使用 `pip install mcp-use`，并通过 `server.run(transport="streamable-http", port=8000)` 启动。
- README 说明 inspector 可通过 `/inspector` 访问，用于交互式调试 MCP server。
- README 也给出 TypeScript 示例：`MCPServer` + `server.listen(3000)` 并提供 inspector 地址。

### FAQ

- **必须用 TypeScript 吗？**：不必须：README 同时提供 Python quickstart；项目内建议选定一种主栈。
- **Inspector 在哪里？**：README 示例显示本地 server 端口下的 `/inspector` 用于调试。
- **生产环境要部署什么？**：部署 MCP server 的对外端点即可；Inspector 建议仅在受信环境开放。

## Source & Thanks

> Created by [mcp-use](https://github.com/mcp-use). Licensed under MIT.
>
> [mcp-use/mcp-use](https://github.com/mcp-use/mcp-use) — ⭐ 9952


---
Source: https://tokrepo.com/en/workflows/mcp-use-fullstack-sdk-for-mcp-servers-apps
Author: MCP Hub