WhiteNightShadow/camoufox-reverse-mcp

🔧 反检测浏览器 MCP Server | 35 个 JS 逆向工具 + C++ 引擎层 JSVMP 指纹追踪

What it solves

This project provides a Model Context Protocol (MCP) server that enables AI coding assistants (like Claude Code, Cursor, and Cline) to perform advanced JavaScript reverse engineering. It solves the difficulty of analyzing protected websites by integrating a fingerprint-resistant browser (Camoufox) with tools for network interception, function hooking, and JSVMP (JavaScript Virtual Machine Protection) analysis, allowing AI agents to automate the process of uncovering API parameters and signature algorithms.

How it works

The server acts as a bridge between an AI agent and a Camoufox browser instance. It exposes a comprehensive set of tools via the MCP protocol, allowing the AI to:

  • Control the Browser: Navigate, take screenshots, and interact with page elements.
  • Analyze Scripts: Search, list, and save JavaScript source code.
  • Perform Hooking: Inject hooks into functions to trace execution and capture data, including presets for XHR, Fetch, and Crypto.
  • Harness Network Analysis: Capture, filter, and intercept network requests and responses.
  • Reverse JSVMP: Use AST-based source instrumentation and runtime probes to analyze virtualized JavaScript code.
  • Engine-Level Tracing: Optionally use a customized browser build to trace native DOM/Web API property access without modifying page JS.

Who it’s for

It is designed for security researchers, reverse engineers, and developers who need to analyze complex anti-bot mechanisms, bypass fingerprinting, and reverse-engineer proprietary JavaScript signatures or encrypted API requests.

Highlights

  • Fingerprint Resistance: Leverages Camoufox's C++ level fingerprint spoofing to avoid common JS-based detection.
  • JSVMP Tooling: Specialized tools for analyzing virtualized JS, including source-level instrumentation and runtime probes.
  • AI-Native Integration: Specifically built as an MCP server for seamless use within AI-powered IDEs.
  • Native Property Tracing: Supports engine-level tracing of Web API access via a custom browser build to provide strong evidence of environment checks.
  • Offline Verification: Includes tools to verify signature functions offline by comparing samples.

Related

  • Project
    WhiteNightShadow/hello_js_reverse_skill

    A comprehensive JavaScript reverse engineering toolkit for AI agents to analyze Web APIs, bypass anti-scraping signatures, and restore encrypted logic in Node.js or Python.

  • Project
    redf0x1/camofox-browser

    CamoFox Browser Server is a TypeScript‑based REST/CLI wrapper around the Camoufox stealth‑Firefox engine. It provides engine‑level fingerprint spoofing, persistent profiles, geo/proxy presets, structured accessibility snapshots, and an encrypted credential vault—making it a robust, anti‑detection browser platform for LLM‑driven agents and other automation tools.

  • 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
    vmoranv/jshookmcp

    A profile‑aware MCP server that gives AI agents a searchable toolbox for front‑end and binary reverse engineering (browser automation, network MITM, WASM decompilation, Frida/Ghidra bridges, APK analysis, etc.). Start with a tiny `search` profile (~3 K tokens) and promote to `full` (733 tools) as needed. Supports stdio or a shared Streamable HTTP daemon, hot‑reload plugins, and session recovery.

  • Project
    jo-inc/camofox-browser

    camofox-browser is a Node‑JS server that runs a fingerprint‑spoofed Firefox (Camoufox) and offers a REST API for AI agents to browse the web undetected. It returns compact accessibility snapshots, supports stable element refs, cookie import, proxy/GeoIP, tracing, and can be deployed via Docker, Fly.io, or Railway.