Usage

MCP Server

Browser Use provides a hosted Model Context Protocol (MCP) server that lets AI models control browser automation directly. Connect Claude, LM Studio, or any MCP-compatible AI to perform web tasks automatically.

MCP Server URL: https://api.browser-use.com/mcp/

Quick Setup

1. Get API Key

Get your API key from the Browser Use Dashboard

2. Connect Your AI

For services supporting MCP servers, update your MCP configuration file:

1{
2  "mcpServers": {
3    "browser_use": {
4      "url": "https://api.browser-use.com/mcp/",
5      "headers": {
6        "X-Browser-Use-API-Key": "Your-API-Key-Here"
7      }
8    }
9  }
10}

Available Tools

The MCP server provides two tools:

browser_task

Creates and runs a browser automation task.

  • task (required): What you want the browser to do
  • max_steps (optional): Max actions to take (1-15, default: 10)

get_browser_task_status

Checks task progress with smart polling.

  • task_id (required): Task ID to check
  • enable_polling (optional): Auto-poll for 45s (default: true)

Example Usage

Once connected, ask your AI to perform web tasks:

“Search Google for the latest iPhone reviews and summarize the top 3 results”

“Go to Hacker News and get me the titles of the top 5 posts”

“Fill out the contact form on example.com with my information”

The AI will use the browser tools automatically to complete these tasks.

Smart Features

Intelligent Polling

When you check task status, the server automatically:

  • Polls every 4 seconds for up to 28 seconds
  • Provides smart recommendations based on how long the task has been running
  • Tells you whether to wait more or take action

Status Messages

Get clear guidance on what to do next:

  • Under 5 minutes: “Recommend trying get_browser_task_status again”
  • Over 5 minutes: “Consider checking live_url or stopping if stuck”

Troubleshooting

Connection issues?

  • Verify your API key is correct
  • Check you’re using the right headers

Task taking too long?

  • Check the live_url to see progress
  • Increase max_steps for complex tasks
  • Use clearer, more specific instructions

Need help? Check the v2 API Reference for detailed specifications.