- Mcp Browser
Mcp Browser
What is MCPBrowser?
MCPBrowser is a browser automation tool designed for web scraping when standard HTTP requests fail. It is particularly useful for accessing web pages that require authentication, have anti-bot protections, or need JavaScript rendering.
How to use MCPBrowser?
To use MCPBrowser, install it as a VS Code extension, npm package, or through Claude Code. Once set up, you can instruct your AI assistant to fetch web pages, fill forms, and extract content using simple commands.
Key features of MCPBrowser?
- Automates web interactions using a real browser session.
- Handles authentication, CAPTCHAs, and anti-bot protections.
- Supports JavaScript-heavy sites and dynamic content loading.
- Provides a set of tools for fetching pages, clicking elements, typing text, and extracting HTML.
Use cases of MCPBrowser?
- Scraping data from corporate intranets that require login.
- Accessing content behind CAPTCHAs or Cloudflare challenges.
- Automating interactions with single-page applications (SPAs).
FAQ from MCPBrowser?
- Can MCPBrowser handle all types of web pages?
No, it is designed for pages that require authentication or have anti-bot measures. For simple HTML pages, standard HTTP requests are sufficient.
- Is MCPBrowser free to use?
Yes, MCPBrowser is open-source and free to use.
- What browsers are supported?
MCPBrowser works with Chrome and Edge.
Server Config
{
"mcpServers": {
"MCPBrowser": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcpbrowser@latest"
],
"description": "Browser automation for web scraping when standard HTTP requests fail. Use ONLY when pages require: (1) Authentication - login forms, SSO, 401/403 errors, corporate intranets, (2) Anti-bot protection - CAPTCHA, Cloudflare challenges, rate limiting, (3) JavaScript rendering - SPAs, dynamic content loaded after page load. Can fetch pages, click elements, fill forms, and extract content. Opens real browser for user authentication, then automates interactions and extraction. DO NOT use for simple HTML pages that work with regular HTTP GET requests."
}
}
}