How to control your browser using Browser MCP

This guide demonstrates how to use the Browser MCP Chrome extension to programmatically control your browser through the Model Context Protocol (MCP). You'll learn how to install and configure the extension, and use the MCP Inspector to execute browser automation commands such as navigating to websites.

What is Browser MCP?

Browser MCP is a Chrome extension that exposes your browser as an MCP (Model Context Protocol) server, allowing AI assistants and automation tools to control browser actions. It enables automated browsing, page navigation, element interaction, and data extraction through standardized MCP commands without requiring access to Chrome's internal DevTools Protocol.

Quick reference commands

# Run MCP Inspector
npx -y @modelcontextprotocol/inspector npx -y @browsermcp/mcp@latest

Read more about the MCP inspector at: Model Context Protocol (MCP) Inspector

Control your browser using Browser MCP video

The following video shows how to control your Chrome browser using the Browser MCP extension step-by-step. The video covers installing and configuring the Chrome extension, launching the MCP Inspector, and executing browser automation commands.

Step 1 - Install the Browser MCP Chrome extension

Navigate to the Browser MCP website and click the Add to Chrome button to open the Chrome Web Store page for the extension (Figure 1).

Open Browser MCP website and press Add to Chrome — Figure 1 - Open Browser MCP website and click Add to Chrome

In the Chrome Web Store, click the Add to Chrome button to install the Browser MCP extension into your browser (Figure 2).

Add the extension to Chrome — Figure 2 - Add Browser MCP extension to Chrome

After installation, pin the extension to keep it easily accessible in your toolbar (Figure 3).

Figure 3 - Pin Browser MCP extension to toolbar

Step 2 - Connect the extension

Click the Browser MCP extension icon in the toolbar to open the extension popup, then click the Connect button to start the local MCP server and make your browser available for automation (Figure 4).

Open extension and connect — Figure 4 - Open Browser MCP extension and connect

Step 3 - Run MCP Inspector

Open a terminal window by searching for "Terminal" in the start menu and clicking on the application. The terminal provides a command-line interface where you'll run the MCP Inspector (Figure 5).

In the terminal, execute the command npx -y @modelcontextprotocol/inspector npx -y @browsermcp/mcp@latest to launch the MCP Inspector with Browser MCP server integration (Figure 6).

npx -y @modelcontextprotocol/inspector npx -y @browsermcp/mcp@latest

You need Node.js and NPM installed on your system to run this command. If you don't have Node.js installed, download it from nodejs.org before proceeding.

Run MCP Inspector with Browser MCP argument — Figure 6 - Execute MCP Inspector command with Browser MCP integration

Wait for the MCP Inspector to download all required dependencies and initialize. Once initialization completes, the MCP Inspector will automatically open in your default web browser and display the connection interface (Figure 7).

Figure 7 - Wait for MCP Inspector to start

Step 4 - Connect to Browser MCP server

In the Inspector interface, the connection settings should already be pre-configured for the Browser MCP server. The transport type should be set to stdio, which is the communication method used between the inspector and the MCP server. Click the Connect button to establish the connection (Figure 8).

Step 5 - List available tools

Once the connection is successful, navigate to the Tools tab and click the List Tools button to display all available browser automation tools provided by the Browser MCP server (Figure 9).

Step 6 - Test tools

Locate and select the browser_navigate tool from the available tools list. In the tool's parameter field, enter the website URL you want to visit, such as https://ozeki.hu. Click the Run Tool button to execute the navigation command (Figure 10).

Execute the browser navigate tool — Figure 10 - Execute browser_navigate tool with target URL

Switch to the Chrome browser window to check the result. The browser has successfully navigated to the specified website. This confirms the automation pipeline is working correctly (Figure 11).

Website opened in Chrome — Figure 11 - Website successfully loaded in Chrome browser

To sum it up

You have successfully installed and tested the Browser MCP Chrome extension for programmatic browser automation. This integration enables you to control your Chrome browser through the Model Context Protocol interface, opening possibilities for automated testing, AI-driven browsing, and integration with AI assistants that support MCP.