Browser MCP logo

Browser MCP

by browsermcp

Browser MCP is an MCP server designed for automating the user's existing browser. It leverages the user's logged-in sessions and avoids bot detection mechanisms.

View on GitHub

Last updated: N/A

What is Browser MCP?

Browser MCP is a server adapted from the Playwright MCP server that automates the user's existing browser instead of creating new instances. It allows for using logged-in sessions and bypassing bot detection.

How to use Browser MCP?

Currently, the core MCP code cannot be built on its own due to dependencies on utils and types from the monorepo where it's developed. Refer to the documentation at https://docs.browsermcp.io for usage instructions once available.

Key features of Browser MCP

  • Automates existing browser instances

  • Uses logged-in sessions

  • Avoids bot detection

  • Adapted from Playwright MCP server

Use cases of Browser MCP

  • Automating tasks within a user's existing browser session

  • Web scraping while avoiding bot detection

  • Testing web applications using existing user profiles

  • Automating workflows that require logged-in accounts

FAQ from Browser MCP

What is MCP?

MCP stands for Machine Control Protocol, a protocol for controlling browsers.

Is Browser MCP related to Playwright?

Yes, Browser MCP was adapted from the Playwright MCP server.

Where can I find the documentation?

The documentation is available at https://docs.browsermcp.io.

Can I build this project directly from this repository?

Currently, the core MCP code cannot be built on its own due to dependencies on utils and types from the monorepo.

What are the benefits of using Browser MCP over creating new browser instances?

Browser MCP allows using the user's existing browser profile to use logged-in sessions and avoid bot detection mechanisms.