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.
MCP server for browser automation using the browser-use library.
This repository contains the server for the browser-use library, which provides a powerful browser automation system that enables AI agents to interact with web browsers through natural language. The server is built on Anthropic's Model Context Protocol (MCP) and provides a seamless integration with the browser-use library. It allows for automated browser interactions such as navigation, form filling, clicking, and scrolling, along with tab management and screenshot functionality. The server also supports a custom agent system with vision-based element detection and structured JSON responses for actions. Configuration is environment-based, allowing for easy setup of API keys and settings.
Features
- Automated browser interactions via natural language
- Custom agent implementation with vision-based element detection
- Environment-based configuration for API keys and settings
