What is Mcp Use

mcp-use is an open-source Unified MCP Client Library designed to connect any LLM (Large Language Model) to any MCP server using TypeScript/Node.js, enabling the creation of custom agents with tool access without relying on closed-source dependencies.

Use cases

Use cases for mcp-use include building chatbots, automating data processing tasks, creating interactive web applications, and developing custom AI agents that require access to multiple tools and servers.

How to use

To use mcp-use, developers can create an MCP-capable agent by writing just a few lines of TypeScript code, leveraging the LangChain.js framework to connect to various tools such as web browsing and file operations.

Key features

Key features include ease of use for quick agent creation, flexibility to work with any LangChain.js-supported LLM, direct HTTP/SSE connection to MCP servers, dynamic server selection, multi-server support, tool restrictions for safety, and the ability to build custom agents.

Where to use

mcp-use can be utilized in various fields such as AI development, automation, web applications, and any scenario where integration with LLMs and MCP servers is required.

Unified MCP Client Library

🌐 MCP Client is the open-source way to connect any LLM to any MCP server in TypeScript/Node.js, letting you build custom agents with tool access without closed-source dependencies.

💡 Let developers easily connect any LLM via LangChain.js to tools like web browsing, file operations, 3D modeling, and more.

✨ Key Features

🚀 Quick Start

Requirements

• Node.js 22.0.0 or higher
• npm, yarn, or pnpm (examples use pnpm)

Installation

# Install from npm
npm install mcp-use
# LangChain.js and your LLM provider (e.g., OpenAI)
npm install langchain @langchain/openai dotenv

Create a .env:

OPENAI_API_KEY=your_api_key

Basic Usage

import { ChatOpenAI } from '@langchain/openai'
import { MCPAgent, MCPClient } from 'mcp-use'
import 'dotenv/config'

async function main() {
  // 1. Configure MCP servers
  const config = {
    mcpServers: {
      playwright: { command: 'npx', args: ['@playwright/mcp@latest'] }
    }
  }
  const client = MCPClient.fromDict(config)

  // 2. Create LLM
  const llm = new ChatOpenAI({ modelName: 'gpt-4o' })

  // 3. Instantiate agent
  const agent = new MCPAgent({ llm, client, maxSteps: 20 })

  // 4. Run query
  const result = await agent.run('Find the best restaurant in Tokyo using Google Search')
  console.log('Result:', result)
}

main().catch(console.error)

📂 Configuration File

You can store servers in a JSON file:

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "@playwright/mcp@latest"
      ]
    }
  }
}

Load it:

import { MCPClient } from 'mcp-use'

const client = MCPClient.fromConfigFile('./mcp-config.json')

🔄 Multi-Server Example

const config = {
  mcpServers: {
    airbnb: { command: 'npx', args: ['@openbnb/mcp-server-airbnb'] },
    playwright: { command: 'npx', args: ['@playwright/mcp@latest'] }
  }
}
const client = MCPClient.fromDict(config)
const agent = new MCPAgent({ llm, client, useServerManager: true })
await agent.run('Search Airbnb in Barcelona, then Google restaurants nearby')

🔒 Tool Access Control

const agent = new MCPAgent({
  llm,
  client,
  disallowedTools: ['file_system', 'network']
})

👥 Contributors

Zane	Pietro Zullo

📜 License

MIT © Zane