Browser Use MCP server

Browser Use MCP Server enables web automation through natural language commands. It provides an API that allows Language Models to navigate websites, complete forms, interact with elements, and perform various web tasks. This server integrates with Model Context Protocol (MCP) clients to empower AI systems with browsing capabilities.

Installation

Install the Package

Install with a specific provider (e.g., OpenAI):

pip install -e "git+https://github.com/yourusername/browser-use-mcp.git#egg=browser-use-mcp[openai]"

Or install all providers:

pip install -e "git+https://github.com/yourusername/browser-use-mcp.git#egg=browser-use-mcp[all-providers]"

Install Playwright browsers:

playwright install chromium

Configure your MCP Client

Add the browser-use-mcp server to your MCP client configuration:

{
    "mcpServers": {
        "browser-use-mcp": {
            "command": "browser-use-mcp",
            "args": ["--model", "gpt-4o"],
            "env": {
                "OPENAI_API_KEY": "your-openai-api-key",  // Or any other provider's API key
                "DISPLAY": ":0"  // For GUI environments
            }
        }
    }
}

Replace "your-openai-api-key" with your actual API key or use an environment variable reference like process.env.OPENAI_API_KEY.

Usage Examples

Using with mcp-use (Python)

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 MCPClient from config file
    client = MCPClient(
        config={
            "mcpServers": {
                "browser-use-mcp": {
                    "command": "browser-use-mcp",
                    "args": ["--model", "gpt-4o"],
                    "env": {
                        "OPENAI_API_KEY": os.getenv("OPENAI_API_KEY"),
                        "DISPLAY": ":0",
                    },
                }
            }
        }
    )

    # 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(
        """
        Navigate to https://github.com, search for "browser-use-mcp", and summarize the project.
        """,
        max_steps=30,
    )
    print(f"\nResult: {result}")

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

Using with Claude for Desktop

1. Open Claude for Desktop
2. Go to Settings → Experimental features
3. Enable Claude API Beta and OpenAPI schema for API
4. Add the following configuration to your Claude Desktop config file:
   • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %AppData%\Claude\claude_desktop_config.json

{
    "mcpServers": {
        "browser-use": {
            "command": "browser-use-mcp",
            "args": ["--model", "claude-3-opus-20240229"]
        }
    }
}

5. Start a new conversation with Claude and ask it to perform web tasks

Supported LLM Providers

The following LLM providers are supported for browser automation:

For more information, check out: https://python.langchain.com/docs/integrations/chat/

You can create a .env file in the project directory with your API keys:

OPENAI_API_KEY=your_openai_key_here
# Or any other provider key

Troubleshooting

• API Key Issues: Ensure your API key is correctly set in your environment variables or .env file.
• Provider Not Found: Make sure you've installed the required provider package.
• Browser Automation Errors: Check that Playwright is correctly installed with playwright install chromium.
• Model Selection: If you get errors about an invalid model, try using the --model flag to specify a valid model for your provider.
• Debug Mode: Use --debug to enable more detailed logging that can help identify issues.
• MCP Client Configuration: Make sure your MCP client is correctly configured with the right command and environment variables.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.