Browser Use Mcp Server

Name: Browser Use Mcp Server
Author: bytedance

@bytedance

About Browser Use Mcp Server

Browser automation capabilities using Puppeteer. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

#puppeteer #browser-use #vnc #llm-optimized

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": [
        "@agent-infra/mcp-server-browser@latest"
      ]
    }
  }
}

Tools

Navigate to a URL

Take a screenshot of the current page or a specific element

Click an element on the page

Fill out an input field

Select an element on the page with index

Hover an element on the page

Execute JavaScript in the browser console

Get the HTML content of the current page, return long text is not friendly to models with limited token, recommended for use browser_get_markdown instead

Get the clickable or hoverable or selectable elements on the current page

Get the text content of the current page

Get the markdown content of the current page

Get all links on the current page

Scroll the page

Go back to the previous page

Go forward to the next page

Get the list of tabs

Open a new tab

Close the current tab

Switch to a specific tab

Overview

What is Browser Use MCP Server?

Browser Use MCP Server is a Model Context Protocol (MCP) server that provides browser automation capabilities using Puppeteer. It enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

How to use Browser Use MCP Server?

Install by adding a JSON configuration to your MCP client (VS Code, Cursor, Windsurf, Claude Desktop, or any MCP client) using the command npx @agent-infra/mcp-server-browser@latest. The server supports local (stdio) mode by default, remote mode via SSE or Streamable HTTP by specifying a --port argument, and in-memory calls for JavaScript/TypeScript projects. Key configuration arguments include --browser, --cdp-endpoint, --headless, --proxy-server, --user-agent, and --viewport-size.

Key features of Browser Use MCP Server

Fast and lightweight using Puppeteer's label index and accessibility DOM tree.
LLM-optimized: operates on structured data, no vision models needed.
Cross-platform and extensible with support for remote and local browsers.
Works with any MCP client: VS Code, Cursor, Windsurf, Claude Desktop.
Supports multiple transport modes: stdio, SSE, and Streamable HTTP.
Offers in-memory integration for JavaScript/TypeScript MCP clients.

Use cases of Browser Use MCP Server

LLM agents navigating and interacting with web pages via structured accessibility snapshots.
Automating browser tasks without requiring visual or screenshot-based models.
Extracting structured data from web pages in a token-efficient manner.
Running browser automation remotely over SSE or Streamable HTTP.

FAQ from Browser Use MCP Server

What makes this different from screenshot-based browser automation?

It uses Puppeteer's accessibility DOM tree and label index instead of pixel-based input, requiring no vision models and consuming less context tokens.

What are the runtime requirements?

Node.js 18 or newer is required, along with any MCP client such as VS Code, Cursor, Windsurf, or Claude Desktop.

How does the server connect to a browser?

It can launch a local browser (default), connect via a CDP endpoint (--cdp-endpoint), a WebSocket endpoint (--ws-endpoint), or use a custom browser executable path (--executable-path).