About mcp-browser-use-tools
An MCP server that packages a subset of browser-use's internal tools with minimal dependencies, for developers building their own agent loop. It does not include the full browser-use agent.
Key features
- 01Google search
- 02URL navigation and back
- 03Clicking elements and entering text
- 04Tab switching and opening
- 05Page extraction and scrolling
- 06Reading and selecting dropdown options
Use cases
- 01Adding web search to a custom agent
- 02Automating page navigation and interaction
- 03Extracting web content for later processing
MCP support
The MCP server exposes a set of browser-use browser-operation tools to clients; it does not provide the full browser-use agent.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-browser-use-tools
This package vendors a subset of browser-use with minimal dependencies exposed as an mcp-server.
Note this does not wrap the full browser-use agent. There are other MCP's that do that. This one only exposes the internal tools for folks who want to roll their own agent loop.
Supports the following tools:
- 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
- select_dropdown_option
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.