MCP Browser Use Tools

@phact

Basic information

About MCP Browser Use Tools

This package vendors a subset of [browser-use](https://github.com/browser-use/browser-use) with minimal dependencies exposed as an mcp-server.

#browser-automation #mcp-tools #mcp-server

MCP Browser Use Tools config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

MCP Browser Use Tools tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-browser-use-tools?

mcp-browser-use-tools vendors a subset of browser-use with minimal dependencies and exposes them as an MCP server. It is intended for developers who want to roll their own agent loop using individual browser automation tools rather than the full browser-use agent.

How to use mcp-browser-use-tools?

The server is used as an MCP server; the README does not provide specific installation or configuration commands. It exposes a set of tools that can be invoked by an MCP client.

Key features of mcp-browser-use-tools

Vendors a subset of browser-use with minimal dependencies.
Exposes 16 individual browser automation tools.
Does not wrap the full browser-use agent.
Allows custom agent loops by using tools directly.
Supports navigation, interaction, and content extraction.

Use cases of mcp-browser-use-tools

Building a custom browser automation agent with fine-grained control.
Performing specific browser actions (click, input, scroll) without a full agent.
Integrating browser automation into an existing MCP-based workflow.

Frequently asked questions

What is the difference between this and other browser-use MCP servers?

This server only exposes the internal tools from browser-use, not the full agent. Other MCP servers wrap the complete browser-use agent.

What tools are available?

The server supports: done, search_google, go_to_url, go_back, wait, click_element, input_text, switch_tab, open_tab, extract_content, scroll_down, scroll_up, send_keys, scroll_to_text, get_dropdown_options, and select_dropdown_option.

What are the dependencies?

The package vendors a subset of browser-use with minimal dependencies, but specific runtime requirements are not detailed in the README.

Comments

More Browser Automation MCP servers

Full Self Browsing

Lakshman Turlapati

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

194

Puppeteer

modelcontextprotocol

Model Context Protocol Servers

88.1K

Live Web Data by Teneo Protocol

Teneo Labs Inc.

Web scraping and fetch API for AI agents: retrieve any public URL live as clean Markdown or HTML, with geo-targeting per request (choose the country) for localized search results and prices, plus optional JavaScript rend

Nullprint

nullprintai

Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive browser profiles in Nullprint, the AI antidetect browser. Install with one command.

Parse

Parse.bot

Parse allows your agent to access thousands of APIs instantly. You can use Parse to build an API for any action on any website and edit any previously existing API in our catalogue.