jsreverser-mcp-javascript-reverse-engineering: Claude Code skill
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.
no license 223 installs ★ 9 updated 2026-10-09
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a claude-codeWhat jsreverser-mcp-javascript-reverse-engineering 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.
What it helps with
- 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 for the agent
- 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
How to install jsreverser-mcp-javascript-reverse-engineering
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a claude-code2Manually: put the files in place
~/.claude/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/jsreverser-mcp-javascript-reverse-engineering/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a codex2Manually: put the files in place
.agents/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a cursor2Manually: put the files in place
.cursor/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/mcp-skills skills/jsreverser-mcp-javascript-reverse-engineering2Manually: put the files in place
.github/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/jsreverser-mcp-javascript-reverse-engineeringManually: put the files in place
.devin/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about jsreverser-mcp-javascript-reverse-engineering
How to install jsreverser-mcp-javascript-reverse-engineering in Claude Code?
Run npx skills add reason-machines/mcp-skills --skill jsreverser-mcp-javascript-reverse-engineering -a claude-code. The file will be placed at ~/.claude/skills/jsreverser-mcp-javascript-reverse-engineering/SKILL.md.
What does jsreverser-mcp-javascript-reverse-engineering do?
It coordinates browser-based reverse engineering tasks, giving the agent a strict workflow: inspect assets first, capture runtime data via non-intrusive hooks, and pause execution with breakpoints only when necessary.
Which features require an external AI provider?
The understand_code tool strictly requires an external model key (Anthropic, OpenAI, or Gemini), while detect_crypto and risk_panel use it optionally to improve recognition quality.