mcp-browser-use-tools

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.

FAQ from mcp-browser-use-tools

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.