mcp_browser_use
If you are the rightful owner of mcp_browser_use and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
This project aims to empower AI agents to perform web use, browser automation, scraping, and automation with Model Context Protocol (MCP) and Selenium.
The MCP Browser Use project is designed to enable AI agents to autonomously perform web-related tasks such as browsing, automation, and data scraping using the Model Context Protocol (MCP) and Selenium. The primary goal is to allow AI agents to complete web tasks with minimal human intervention, guided by natural language instructions. Users are required to set up a Python environment and configure the MCP server to interact with the browser. The project provides a set of tools that can be used to automate various browser actions, such as clicking elements, filling text, navigating URLs, and more. The setup involves configuring a JSON file to point to the correct Python executable and ensuring all dependencies are installed. Once configured, users can interact with the MCP tools through a user interface, which displays available functions and their descriptions.
Features
- Browser Automation: Automate web tasks using natural language instructions.
- Selenium Integration: Leverage Selenium for robust browser interactions.
- MCP Tools: Access a variety of tools for web automation tasks.
- Configurable Environment: Set up a Python environment for MCP server operations.
- User Interface: Visual interface to view and use available MCP tools.
Tools
click_element
Click on the element on the page
close_browser
Close the browser session
fill_text
Enter text into the input field
navigate
Navigate to the specified URL
scroll
Scroll the page
send_keys
Send keyboard keys to the browser
start_browser
Start a new browser session
take_screenshot
Take screenshot of the current page