Skip to main content

​
Quickstart Guide

This guide will get you started with mcp_use in under 5 minutes. We’ll cover installation, basic configuration, and running your first agent.

​
Installation

  pip install mcp-use
Installing from source gives you access to the latest features and examples!

​
Installing LangChain Providers

mcp_use works with various LLM providers through LangChain. You’ll need to install the appropriate LangChain provider package for your chosen LLM: 
  pip install langchain-openai
Tool Calling Required: Only models with tool calling capabilities can be used with mcp_use. Make sure your chosen model supports function calling or tool use.
For other providers, check the LangChain chat models documentation

​
Environment Setup

Set up your environment variables in a .env file for secure API key management:
.env
OPENAI_API_KEY=your_api_key_here
ANTHROPIC_API_KEY=your_api_key_here
GROQ_API_KEY=your_api_key_here
GOOGLE_API_KEY=your_api_key_here

​
Your First Agent

Here’s a simple example to get you started: 
  import asyncio
  import os
  from dotenv import load_dotenv
  from langchain_openai import ChatOpenAI
  from mcp_use import MCPAgent, MCPClient

  async def main():
      # Load environment variables
      load_dotenv()

      # Create configuration dictionary
      config = {
        "mcpServers": {
          "playwright": {
            "command": "npx",
            "args": ["@playwright/mcp@latest"],
            "env": {
              "DISPLAY": ":1"
            }
          }
        }
      }

      # Create MCPClient from configuration dictionary
      client = MCPClient(config)

      # Create LLM
      llm = ChatOpenAI(model="gpt-4o")

      # Create agent with the client
      agent = MCPAgent(llm=llm, client=client, max_steps=30)

      # Run the query
      result = await agent.run(
          "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
      )
      print(f"\nResult: {result}")

  if __name__ == "__main__":
      asyncio.run(main())

​
Configuration Options

You can also load servers configuration from a config file: 
  client = MCPClient.from_config_file("browser_mcp.json")
Example configuration file (browser_mcp.json): 
{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"],
      "env": {
        "DISPLAY": ":1"
      }
    }
  }
}
For multi-server setups, tool restrictions, and advanced configuration options, see the Configuration Overview.

​
Available MCP Servers

mcp_use supports any MCP server. Check out the Awesome MCP Servers list for available options.

​
Streaming Agent Output

Stream agent responses as they’re generated: 
  async for chunk in agent.stream("your query here"):
      print(chunk, end="", flush=True)
Uses LangChain’s streaming API. See streaming documentation for more details.

​
Next Steps

Configuration

Complete configuration guide covering client setup and agent customization

LLM Integration

Discover all supported LLM providers and optimization tips

Examples

Explore real-world examples and use cases
Need Help? Join our community discussions on GitHub or check out the comprehensive examples in our repository!