js-reverse-mcp
Active·★ 3.0k·Apache-2.0·Updated 2026-09-03
JS Reverse MCP is an AI-first server designed for JavaScript reverse engineering, enabling AI coding assistants to debug, locate, save, and analyze web page JavaScript behavior like human analysts. It provides AI-native tools that re-organize browser capabilities for continuous inference and operation, including anti-detection features to bypass sophisticated anti-crawling mechanisms.
#JavaScript Reverse Engineering#AI Agent#Browser Automation#Anti-detection#Debugging#Web Analysis#CDP#Playwright
01
Features
01AI-native Tool Design
02Replayable Workflow
03Breakpoint Context Execution
04Advanced Anti-detection Layer
05Comprehensive Script and Network Analysis
02
Compatibility
Node.js
Runtime
Verified via docs
Chrome
Browser
Verified via docs
AI Agent Platforms
Integration
Verified via docs
03
Quick start
1
$ git clone https://github.com/zhizhuodemao/js-reverse-mcp.git
2
$ cd js-reverse-mcp
3
$ npm install
4
$ npm run build
04
Use cases
↳Automated JavaScript reverse engineering workflows for AI agents
↳Analyzing WebSocket communication patterns and messages
↳Replaying and analyzing cookie generation and anti-fraud processes
↳Debugging and inspecting JavaScript behavior on complex web pages
05
Alternatives
jshookmcp★ 2.1k
A search-first, profile-aware reverse-engineering workspace for AI agents — 735 tools across 36 domains in one MCP server.
invisible_playwright_mcp★ 887
Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.
CyberStrike★ 3.3k
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK, OWASP WSTG, CIS Benchmarks. Post-exploit: Linux/Windows/macOS/AWS/Azure/K8s/CI-CD. Web UI + Cloudflare Tunnel. Your AI red team.
OpenOSINT★ 1.8k
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 9 tools. Works with Claude, GPT-4, or local models. For authorized security research only.
Comments
Log in to leave a comment
No comments yet. Be the first!