MCP Use▌

## About mcp-use 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 - **Preview** on mcp-use MCP Inspector ([online](https://inspector.mcp-use.com/inspector) | [oss](https://github.com/mcp-use/mcp-use/tree/main/libraries/typescript/packages/inspector)): Test and debug your MCP Servers and Apps - **Deploy** on [Manufact MCP Cloud](https://manufact.com): Connect your GitHub repo and have your MCP Server and App up and running in production with observability, metrics, logs, branch-deployments, and more ## Documentation Visit our [docs](https://mcp-use.com/docs) or jump to a quickstart ([TypeScript](https://mcp-use.com/docs/typescript/getting-started/quickstart) | [Python](https://mcp-use.com/docs/python/getting-started/quickstart)) ### Skills for Coding Agents > **Using Claude Code, Codex, Cursor or other AI coding agents?** > > **[Install mcp-use skill for MCP Apps](https://skills.sh/mcp-use/mcp-use/mcp-apps-builder)** ## Quickstart: MCP Servers and MCP Apps ### TypeScript Build your first MCP Server or MPC App: ```bash npx create-mcp-use-app@latest ``` Or create a server manually: ```typescript import { MCPServer, text } from "mcp-use/server"; import { z } from "zod"; const server = new MCPServer({ name: "my-server", version: "1.0.0", }); server.tool({ name: "get_weather", description: "Get weather for a city", schema: z.object({ city: z.string() }), }, async ({ city }) => { return text(`Temperature: 72°F, Condition: sunny, City: ${city}`); }); await server.listen(3000); // Inspector at http://localhost:3000/inspector ``` [**→ Full TypeScript Server Documentation**](https://mcp-use.com/docs/typescript/server) ## MCP Apps MCP Apps let you build interactive widgets that work across Claude, ChatGPT, and other MCP clients — write once, run everywhere. **Server**: define a tool and point it to a widget: ```typescript import { MCPServer, widget } from "mcp-use/server"; import { z } from "zod"; const server = new MCPServer({ name: "weather-app", version: "1.0.0", }); server.tool({ name: "get-weather", description: "Get weather for a city", schema: z.object({ city: z.string() }), widget: "weather-display", // references resources/weather-display/widget.tsx }, async ({ city }) => { return widget({ props: { city, temperature: 22, conditions: "Sunny" }, message: `Weather in ${city}: Sunny, 22°C`, }); }); await server.listen(3000); ``` **Widget**: create a React component in `resources/weather-display/widget.tsx`: ```tsx import { useWidget, type WidgetMetadata } from "mcp-use/react"; import { z } from "zod"; const propSchema = z.object({ city: z.string(), temperature: z.number(), conditions: z.string(), }); export const widgetMetadata: WidgetMetadata = { description: "Display weather information", props: propSchema, }; const WeatherDisplay: React.FC = () => { const { props, isPending, theme } = useWidget>(); const isDark = theme === "dark"; if (isPending) return

Loading...

; return (

{props.city}

{props.temperature}° — {props.conditions}

); }; export default WeatherDisplay; ``` Widgets in `resources/` are **auto-discovered** — no manual registration needed. Visit [**MCP Apps Documentation**](https://mcp-use.com/docs/typescript/server/ui-widgets) --- ### Python ```bash pip install mcp-use ``` ```python from typing import Annotated from mcp.types import ToolAnnotations from pydantic import Field 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"Temperature: 72°F, Condition: sunny, City: {city}" # Start server with auto-inspector server.run(transport="streamable-http", port=8000) # 🎉 Inspector at http://localhost:8000/inspector ``` [**→ Full Python Server Documentation**](https://mcp-use.com/docs/python/server/index) --- ## Inspector The mcp-use Inspector lets you test and debug your MCP servers interactively. **Auto-included** when using `server.listen()`: ```typescript server.listen(3000); // Inspector at http://localhost:3000/inspector ``` **Online** when connecting to hosted MCP servers:
>Visit https://inspector.mcp-use.com **Standalone**: inspect any MCP server: ```bash npx @mcp-use/inspector --url http://localhost:3000/mcp ``` Visit [**Inspector Documentation**](https://mcp-use.com/docs/inspector/index) --- ## Deploy Deploy your MCP server to production: ```bash npx @mcp-use/cli login npx @mcp-use/cli deploy ``` Or connect your GitHub repo on [manufact.com](https://manufact.com) — production-ready with observability, metrics, logs, and branch-deployments. --- ## Package Overview This monorepo contains multiple packages for both Python and TypeScript: ### Python Packages | Package | Description | Version | | ----------- | ------------------------------------- | --------------------------------------------------------------------------------------- | | **mcp-use** | Complete MCP server and MCP agent SDK | [](https://pypi.org/project/mcp_use/) | ### TypeScript Packages | Package | Description | Version | | ---------------------- | ----------------------------------------------- | --------------------------------------------------------------------------------------------------------------- | | **mcp-use** | Core framework for MCP servers, MCP apps, and MCP agents | [](https://www.npmjs.com/package/mcp-use) | | **@mcp-use/cli** | Build tool with hot reload and auto-inspector | [](https://www.npmjs.com/package/@mcp-use/cli) | | **@mcp-use/inspector** | Web-based previewer and debugger for MCP servers | [](https://www.npmjs.com/package/@mcp-use/inspector) | | **create-mcp-use-app** | Project scaffolding tool | [](https://www.npmjs.com/package/create-mcp-use-app) | --- ## Also: MCP Agent & Client mcp-use also provides a full MCP Agent and Client implementation.

Build an AI Agent

### Python ```bash pip install mcp-use langchain-openai ``` ```python import asyncio from langchain_openai import ChatOpenAI from mcp_use import MCPAgent, MCPClient async def main(): config = { "mcpServers": { "filesystem": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"] } } } client = MCPClient.from_dict(config) llm = ChatOpenAI(model="gpt-4o") agent = MCPAgent(llm=llm, client=client) result = ---