vibheksoni/stealth-browser-mcp

Stealth browser automation for AI agents over MCP and the Chrome DevTools Protocol: navigation, network hooks, DOM extraction, and pixel-accurate UI cloning.

What it solves

Stealth Browser MCP allows AI agents to automate web browsing while avoiding detection by anti-bot systems. It enables agents to bypass Cloudflare challenges, login walls, and other bot-detection mechanisms that typically block automated headless browsers.

How it works

The project implements a Model Context Protocol (MCP) server that controls real Chrome-family browser instances (Chrome, Chromium, or Edge). It leverages nodriver and the Chrome DevTools Protocol (CDP) to interact with the browser at a low level, making the automation appear more human-like. It provides a comprehensive set of tools for navigation, element interaction, network inspection, and JavaScript execution, which can be loaded in modular configurations (from a minimal 21-tool core to a full 98-tool suite).

Who it’s for

It is designed for developers building AI agents that require reliable web access, data extraction, or automation on websites with strict anti-bot protections.

Highlights

  • Anti-bot resistance: Capable of passing Cloudflare and Queue-It style challenges.
  • Extensive Toolset: 98 tools across 11 categories, including network debugging and CDP execution.
  • Pixel-accurate cloning: Ability to extract complete UI elements including CSS, DOM structure, and animations.
  • Network Interception: A dynamic hook system that allows agents to intercept, block, or modify request and response flows.
  • Modular Architecture: Supports different modes (Full, Minimal, Xpool-safe) to tailor the tool surface to the agent's needs.
  • Cross-platform: Works on Windows, macOS, Linux, and Docker.

Related

  • Project
    iFurySt/open-browser-use

    Open Browser Use is an open‑source, runtime‑agnostic browser‑automation layer for AI agents. It pairs a Chrome extension with a CLI and provides JavaScript, Python, and Go SDKs plus an MCP server, enabling agents to list tabs, open URLs, navigate, and run CDP actions. Install via npm or Homebrew, run `open-browser-use setup` to register the native host, then add the skill to agents like Codex or Claude‑Code. MIT‑licensed.

  • Project
    brightdata/brightdata-mcp

    An MCP server that gives AI agents real-time web access with built-in bot detection bypass and 69 tools for web search, scraping, and structured data extraction.

  • Project
    zhizhuodemao/js-reverse-mcp

    js‑reverse‑mcp is a Node.js MCP server that lets LLM agents debug and reverse‑engineer JavaScript in Chrome. It wraps DevTools data (scripts, breakpoints, network, WebSocket, storage) into 24 concise tools designed for AI‑driven reasoning, and includes optional stealth layers (Patchright fork and CloakBrowser) for anti‑bot sites.

  • Project
    dondai1234/master-fetch

    An MCP server that gives AI agents free, keyless web search and anti-bot fetching capabilities, allowing them to bypass bot walls and crawl the web locally.