browser-use-mcp-server
by co-browser
An MCP server that enables AI agents to control web browsers using browser-use. It supports both SSE and stdio protocols for communication.
Last updated: N/A
What is browser-use-mcp-server?
browser-use-mcp-server is an MCP (Message Control Protocol) server that allows AI agents to control web browsers programmatically. It acts as a bridge between AI agents and web browsers, enabling automated interactions with web content.
How to use browser-use-mcp-server?
To use the server, you need to install the prerequisites (uv, Playwright, mcp-proxy), configure the environment with your OpenAI API key, and then install the server. You can run it in either SSE or stdio mode, configuring your client accordingly. The README provides detailed instructions for installation, configuration, and running the server in both modes.
Key features of browser-use-mcp-server
Browser Automation
Dual Transport (SSE and stdio)
VNC Streaming
Async Tasks
Use cases of browser-use-mcp-server
Automated web scraping
AI-powered web testing
Web-based task automation
AI agent interaction with web applications
FAQ from browser-use-mcp-server
What is uv?
What is uv?
uv is a fast Python package manager used for installing and managing dependencies.
What is Playwright?
What is Playwright?
Playwright is a browser automation library that allows you to control web browsers programmatically.
What is mcp-proxy?
What is mcp-proxy?
mcp-proxy is required for stdio mode and facilitates communication between the server and the client.
How do I configure the OpenAI API key?
How do I configure the OpenAI API key?
You need to set the OPENAI_API_KEY environment variable in a .env file or directly in the command line.
How do I choose between SSE and stdio mode?
How do I choose between SSE and stdio mode?
SSE mode is simpler to set up, while stdio mode might be preferred in certain environments where direct process communication is required. Client configuration differs based on the chosen mode.