Mcp Browser
@cherchyk
About Mcp Browser
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,
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"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."
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Browser?
MCP Browser is an MCP (Model Context Protocol) server that gives AI assistants (Claude, Copilot) the ability to browse web pages using your real Chrome or Edge browser session. It handles authentication, CAPTCHAs, anti-bot protection, and JavaScript-heavy sites by leveraging your existing logged-in session rather than using headless automation.
How to use MCP Browser?
Install via the VS Code Marketplace extension (one‑click), a single Claude Code command (claude mcp add mcpbrowser), manual configuration in Claude Desktop’s claude_desktop_config.json, or the npx -y mcpbrowser@latest command. After setup, the AI can invoke tools like fetch_webpage, click_element, type_text, get_current_html, and close_tab to interact with web pages.
Key features of MCP Browser
- Uses your own Chrome/Edge browser (not headless).
- Authenticates once – AI inherits your session.
- Handles SSO, CAPTCHAs, Cloudflare, and SPAs.
- Provides tools for navigation, clicking, typing, and content extraction.
- Reduces page size by ~90% when
removeUnnecessaryHTMLis enabled. - Works with Claude Desktop, Claude Code, GitHub Copilot, and any MCP host.
Use cases of MCP Browser
- Automating login flows on sites with corporate SSO or multi‑factor authentication.
- Extracting data from authenticated dashboards (e.g., Azure Portal, admin panels).
- Interacting with JavaScript‑heavy single‑page applications.
- Resetting session state by closing a tab for a fresh login.
- Performing multi‑step workflows that require button clicks and form fills.
FAQ from MCP Browser
What are the requirements to use MCP Browser?
You need Node.js 18+ and either Chrome or Edge browser installed on your machine.
How does MCP Browser connect to my browser?
It launches your local Chrome or Edge in a managed mode and reuses your existing user data directory, so cookies and authentication persist across sessions.
Which AI assistants can use MCP Browser?
Any MCP‑compatible host, including Claude Desktop, Claude Code (CLI), and GitHub Copilot. The VS Code extension auto‑configures it for Copilot.
Can MCP Browser interact with pages after logging in?
Yes. Load the login page with fetch_webpage, then use type_text and click_element to log in. The session stays open, and you can call get_current_html or further tools on the same domain without re‑authenticating.
How do I clear an authenticated session?
Use close_tab with the page’s URL. This closes the associated browser tab and forces a fresh session the next time that domain is visited.
More Browser Automation MCP servers
mcp-browser-use: MCP server for browser-use
vinayak-mehtaMCP server for browser-use
fetch-mcp
egoistAn MCP server for fetching URLs / Youtube video transcript.
Firecrawl Mcp Server
mendableai🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Fastcrw
usFast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.
browser-use-mcp-server
co-browserBrowse the web, directly from Cursor etc.
Comments