Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

mcp-use is the easiest way to interact with mcp servers with custom agents

License

NotificationsYou must be signed in to change notification settings

mcp-use/mcp-use

mcp use logo

Full-Stack MCP Framework

mcp-use provides everything you need to build withModel Context Protocol
MCP servers, MCP clients and AI agents in 6 lines of code, in bothPython andTypeScript.


Badge
Badge


Stack

  • 🤖 MCP Agents - AI agents that can use tools and reason across steps
  • 🔌 MCP Clients - Connect any LLM to any MCP server
  • 🛠️ MCP Servers - Build your own MCP servers
  • 🔍 MCP Inspector - Web-based debugger for MCP servers
  • 🎨 MCP-UI Resources - Build ChatGPT apps with interactive widgets

🚀 What Do You Want to Build?

🤖 Build an AI Agent

Create intelligent agents that can use tools, browse the web, manage files, and more.

Quick Start ↓ |Python Docs |TypeScript Docs

🔌 Use MCP Client

Connect directly to MCP servers and call tools programmatically without an agent.

Quick Start ↓ |Python Docs |TypeScript Docs

🛠️ Create an MCP Server

Build your own MCP servers with tools, resources, and prompts.

Quick Start ↓ |Python Docs |TypeScript Docs

🔍 Debug with Inspector

Test, debug, and explore your MCP servers interactively.

Quick Start ↓ |Inspector Docs |MCP Inspector online

🎨 Build ChatGPT Apps

Create interactive UIs with mcp-ui, react and live reload.

Quick Start |Templates

☁️ Deploy to MCP Cloud

Deploy and manage your MCP agents and servers in the cloud.

Quick Start |Cloud ↗


📦 Quick Start

Build an AI Agent

Create an AI agent that can use MCP tools to accomplish complex tasks.

Python

pip install mcp-use langchain-openai
importasynciofromlangchain_openaiimportChatOpenAIfrommcp_useimportMCPAgent,MCPClientasyncdefmain():# Configure MCP serverconfig= {"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=awaitagent.run("List all files in the directory")print(result)asyncio.run(main())

→ Full Python Agent Documentation

Typescript

npm install mcp-use @langchain/openai
import{ChatOpenAI}from"@langchain/openai";import{MCPAgent,MCPClient}from"mcp-use";asyncfunctionmain(){// Configure MCP serverconstconfig={mcpServers:{filesystem:{command:"npx",args:["-y","@modelcontextprotocol/server-filesystem","/tmp"],},},};constclient=MCPClient.fromDict(config);constllm=newChatOpenAI({modelName:"gpt-4o"});constagent=newMCPAgent({ llm, client});constresult=awaitagent.run("List all files in the directory");console.log(result);}main();

→ Full TypeScript Agent Documentation


Use MCP Client

Connect to MCP servers directly without an AI agent for programmatic tool access.

Python

importasynciofrommcp_useimportMCPClientasyncdefmain():config= {"mcpServers": {"calculator": {"command":"npx","args": ["-y","@modelcontextprotocol/server-everything"]            }        }    }client=MCPClient.from_dict(config)awaitclient.create_all_sessions()session=client.get_session("calculator")result=awaitsession.call_tool(name="add",arguments={"a":5,"b":3})print(f"Result:{result.content[0].text}")awaitclient.close_all_sessions()asyncio.run(main())

→ Python Client Documentation

Typescript

import{MCPClient}from"mcp-use";asyncfunctionmain(){constconfig={mcpServers:{calculator:{command:"npx",args:["-y","@modelcontextprotocol/server-everything"],},},};constclient=newMCPClient(config);awaitclient.createAllSessions();constsession=client.getSession("calculator");constresult=awaitsession.callTool("add",{a:5,b:3});console.log(`Result:${result.content[0].text}`);awaitclient.closeAllSessions();}main();

→ TypeScript Client Documentation


Create an MCP Server

Build your own MCP server with custom tools, resources, and prompts.

Typescript

npx create-mcp-use-app my-servercd my-servernpm install
import{createMCPServer}from"mcp-use/server";import{z}from"zod";constserver=createMCPServer("my-server",{version:"1.0.0",description:"My custom MCP server",});// Define a toolserver.tool("get_weather",{description:"Get weather for a city",parameters:z.object({city:z.string().describe("City name"),}),execute:async({ city})=>{return{temperature:72,condition:"sunny", city};},});// Start server with auto-inspectorserver.listen(3000);// 🎉 Inspector at http://localhost:3000/inspector

→ Full TypeScript Server Documentation

Python

Coming Soon! For now, please use the TypeScript implementation to create MCP servers.


Use the Inspector

Debug and test your MCP servers with the interactive web-based inspector.

Automatic (with mcp-use server)

When you create a server withmcp-use, the inspector is automatically available:

server.listen(3000);// Inspector automatically at: http://localhost:3000/inspector

Standalone

Inspect any MCP server via CLI:

npx @mcp-use/inspector --url http://localhost:3000/sse

Features:

  • 🔍 Test tools interactively with live execution
  • 📊 Monitor connection status and server health
  • 🔐 Handle OAuth flows automatically
  • 💾 Persistent sessions with localStorage

→ Full Inspector Documentation


📚 More Examples & Documentation

Example Use Cases

Complete Documentation


✨ Key Features

FeatureDescriptionPythonTypeScript
🤖 MCP AgentsAI agents with tool access and multi-step reasoning
🔌 MCP ClientsDirect connection to any MCP server
🛠️ MCP ServersBuild custom MCP servers🔜
🔍 InspectorWeb-based debugging tool
🎨 UI WidgetsBuild interactive React UIs
🌐 Multi-ServerConnect to multiple servers simultaneously
📡 StreamingReal-time streaming responses
📊 ObservabilityBuilt-in Langfuse integration
🔐 OAuth SupportBuilt-in OAuth flow handling
🛡️ Tool ControlRestrict access to specific tools

📦 Package Overview

This monorepo contains multiple packages for both Python and TypeScript:

Python Packages

PackageDescriptionVersion
mcp-useComplete MCP client and agent libraryPyPI

TypeScript Packages

PackageDescriptionVersion
mcp-useCore framework for clients, agents, and serversnpm
@mcp-use/cliBuild tool with hot reload and auto-inspectornpm
@mcp-use/inspectorWeb-based debugger for MCP serversnpm
create-mcp-use-appProject scaffolding toolnpm

🏗️ Repository Structure

mcp-use/├── libraries/│   ├── python/              → Python implementation│   │   ├── mcp_use/         → Core library│   │   ├── examples/        → Python examples│   │   └── docs/            → Python documentation│   ││   └── typescript/          → TypeScript implementation│       └── packages/│           ├── mcp-use/     → Core framework│           ├── cli/         → Build tool│           ├── inspector/   → Web inspector│           └── create-mcp-use-app/  → Scaffolding└── README.md               → This file

🌟 Why MCP-Use?

Complete Vertical Stack

Build everything from AI agents to servers - not just clients. Create the full MCP ecosystem in your preferred language.

Language Flexibility

Choose Python for ML/data workflows or TypeScript for web applications. Same great features, different languages.

Production Ready

Includes observability, streaming, multi-server support, sandboxing, and tool access controls out of the box.

Developer Experience

Hot reload, TypeScript/Python type safety, built-in inspector, and comprehensive documentation.

Open Source

MIT licensed and community-driven. Contribute, fork, or extend as needed.


🤝 Community & Support


📜 License

MIT ©MCP-Use Contributors


🙏 Contributing

We love contributions! Check out our contributing guidelines:


⭐ Star History

Star History Chart


📝 Citation

If you use MCP-Use in your research or project, please cite:

@software{mcp_use2025,author ={Zullo, Pietro and Contributors},title ={MCP-Use: Complete MCP Ecosystem for Python and TypeScript},year ={2025},publisher ={GitHub},url ={https://github.com/mcp-use/mcp-use}}

Contributors

Thanks to all our amazing contributors!

Core Contributors

  1. Pietro (@pietrozullo)
  2. Luigi (@pederzh)
  3. Enrico (@tonxxd)


Built with ❤️ by the MCP-Use community
San Francisco | Zürich

Packages

No packages published

[8]ページ先頭

©2009-2025 Movatter.jp