Advertise
MCP.so
Sign In
B

Browser Use MCP Server

@bytedance

Repository

Basic information

Category

Browser Automation

Transports

stdio

Author

bytedance

Submitted by

Charles King

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

Browser Use MCP Server config

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

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

Browser Use MCP Server tools

21

Navigate to a URL

Go back to the previous page

Go forward to the next page

Fill out an input field, before using the tool, Either 'index' or 'selector' must be provided

Get the markdown content of the current page

Get the text content of the current page

Get all links on the current page

Open a new tab

Get the list of tabs

Switch to a specific tab

Close the current tab

Execute JavaScript in the browser console

Get the list of downloaded files

Take a screenshot of the current page or a specific element

Click an element on the page, before using the tool, use `browser_get_clickable_elements` to get the index of the element, but not call `browser_get_clickable_elements` multiple times

Select an element on the page with index, Either 'index' or 'selector' must be provided

Hover an element on the page, Either 'index' or 'selector' must be provided

Get the clickable or hoverable or selectable elements on the current page, don't call this tool multiple times

Scroll the page

Close the browser when the task is done and the browser is not needed anymore

Press a key on the keyboard

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.

Frequently asked questions

1

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.

2

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.

3

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`).

4

What transport protocols are supported?

The server supports the standard MCP stdio transport (local), SSE transport, and Streamable HTTP transport for remote connections.

5

Can I use a proxy with Browser Use MCP Server?

Yes, you can specify a proxy server with `--proxy-server` and bypass domains with `--proxy-bypass`.

Comments

More Browser Automation MCP servers

Playwright MCP Server 🎭

executeautomation

Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌

5.6K
C

Chrome DevTools for agents

ChromeDevTools

Official Chrome DevTools MCP server from Google that lets coding agents control, debug and profile a live Chrome browser.

53.6K

Browse Bridge

Share selected Chrome tabs with AI agents. You enable the tab you want to share and maintain the ability to instantly take control. Browse Bridge is a remote MCP server available at https://mcp.browsebridge.com. What c

Full Self Browsing

Lakshman Turlapati

DOM-first AI browser automation for Chrome and MCP clients.

194

Screenshot Scout

screenshotscout

Capture screenshots of webpages as images or PDFs with Screenshot Scout.

Advertise