# jsreverser-mcp-javascript-reverse-engineering

jsreverser-mcp-javascript-reverse-engineering guides agents through JavaScript reverse engineering in live browsers: runtime function hooking, network call tracing, deobfuscation, and crypto logic extraction.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 223 installs · ★ 9 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/jsreverser-mcp-javascript-reverse-engineering

## What it does

This skill instructs coding assistants to drive the JSReverser-MCP server inside an active browser session. Instead of blindly freezing the execution thread, the agent inspects loaded scripts, traces network requests to their initiators, and inserts lightweight runtime hooks to capture function inputs.

The server exposes distinct toolsets for script discovery, breakpoint manipulation, WebSocket inspection, and AST-level deobfuscation. Once parameters are captured, tools like `deobfuscate_code` and `detect_crypto` help unpack minified routines and isolate signature algorithms for local execution.

Operating this setup requires building the MCP server via `npm run build` and launching Chrome with `--remote-debugging-port=9222`. Semantic analysis via `understand_code` also requires an API key for Anthropic, OpenAI, or Gemini passed into the server environment.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/jsreverser-mcp-javascript-reverse-engineering/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/mcp-skills skills/jsreverser-mcp-javascript-reverse-engineering
```

2. **Manually: put the files in place**
- File: `.github/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/jsreverser-mcp-javascript-reverse-engineering
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md

## When to use it
- trace which function initiated a protected network request
- hook browser crypto methods to record encryption inputs
- clean and deobfuscate minified frontend logic
- extract API signing routines to reproduce them in Node.js

## Example prompts
- Inspect scripts on the page and hook window.crypto.subtle.encrypt to see raw parameters
- Trace the initiator for the POST request sent to /api/v1/auth
- Deobfuscate this minified bundle snippet and check for crypto algorithms

## Similar
- [reverse-engineering-tools](https://affpapa.org/en/nevibecode/skills/reverse-engineering-tools.md) — skill · 575 installs
- [protocol-reverse-engineering](https://affpapa.org/en/nevibecode/skills/protocol-reverse-engineering.md) — skill · 12701 installs
- [reverse-engineering](https://affpapa.org/en/nevibecode/skills/reverse-engineering.md) — skill · 2100 installs
- [learn-reverse-engineering](https://affpapa.org/en/nevibecode/skills/learn-reverse-engineering.md) — skill · 1400 installs
- [reverse-engineering-android-malware-with-jadx](https://affpapa.org/en/nevibecode/skills/reverse-engineering-android-malware-with-jadx.md) — skill · 541 installs
- [reverse-engineering-firmware-analysis](https://affpapa.org/en/nevibecode/skills/reverse-engineering-firmware-analysis.md) — skill · 1 install

From the same set: [reason-machines/mcp-skills](https://affpapa.org/en/nevibecode/by/reason-machines/mcp-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
