back to home

vmoranv / jshookmcp

js hook toolkit that all you need

View on GitHub
978 stars
317 forks
2 issues

AI Architecture Analysis

This repository is indexed by RepoMind. By analyzing vmoranv/jshookmcp in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.

Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.

Source files are only loaded when you start an analysis to optimize performance.

Embed this Badge

Showcase RepoMind's analysis directly in your repository's README.

[![Analyzed by RepoMind](https://img.shields.io/badge/Analyzed%20by-RepoMind-4F46E5?style=for-the-badge)](https://repomind.in/repo/vmoranv/jshookmcp)
Preview:Analyzed by RepoMind

Repository Overview (README excerpt)

Crawler view

@jshookmcp/jshook English | δΈ­ζ–‡ An MCP (Model Context Protocol) server providing **290+ built-in tools** across **17+ domains** (including core meta-tools) β€” with runtime extension loading from and for AI-assisted JavaScript analysis and security analysis. Combines browser automation, Chrome DevTools Protocol debugging, network monitoring, intelligent JavaScript hooks, LLM-powered code analysis, process/memory inspection, WASM toolchain, binary encoding, anti-anti-debug, GraphQL discovery, source map reconstruction, AST transforms, crypto reconstruction, platform package analysis, Burp Suite / native analysis tool bridges, human behavior simulation, CAPTCHA solving, batch account workflows, and high-level composite workflow orchestration in a single server. Documentation / Quick Links β€’ **πŸ“– Read the Documentation** β€’ **πŸš€ Getting Started** β€’ **βš™οΈ Configuration** β€’ **πŸ“š Tool Reference** 🌟 Key Highlights β€’ πŸ€– **AI-Driven Analysis**: Leverage LLMs for intelligent JavaScript deobfuscation, cryptographic algorithm detection, and AST-level code comprehension. β€’ ⚑ **Search-First Context Efficiency**: BM25-powered + dynamic boosts cut jshook's tool-schema init delta from ~40.0K+ tokens ( ) to ~3.0K ( ) (Claude server-side count; excludes Claude Code base prompt). β€’ 🎯 **Progressive Capability Tiers**: Three built-in profiles ( / / ), with as the default base tier for on-demand capability scaling. β€’ 🌐 **Full-Stack Automation**: Seamlessly orchestrate Chromium/Camoufox browsers, CDP debugging, and network interception as atomic actions. β€’ πŸ›‘οΈ **Advanced Anti-Debug**: Built-in evasion for debugger statements, timing checks, and strict headless bot fingerprinting techniques. β€’ 🧩 **Dynamic Extensibility**: Hot-reload plugins and workflows from local directories without recompiling the core server. β€’ πŸ”§ **Zero-Wiring Extensibility**: Auto-discovered domains via , lazy handler instantiation, and B-Skeleton contracts for plugins/workflows. β€’ πŸ› οΈ **Reverse Engineering Toolchain**: Integrated WASM disassembly, binary entropy analysis, in-memory scanning, and bridges for Burp Suite/Ghidra/IDA Pro. Features Provides a comprehensive suite of tools for AI-assisted JavaScript analysis, browser automation, CDP debugging, network interception, memory analysis, and more. > **View the full feature list in the documentation β†—** Architecture & Performance β€’ **Progressive Tool Discovery**: meta-tool (BM25 ranking) + / + profile-based tier upgrades ( ) β€’ **Search-tier behavior**: only searches and ranks results; it does not auto-run , and it does not auto-run . Preferred chain: β€’ **Do not boost for one tool**: can register exact tools across tiers from the current base tier; is better when you expect to reuse a broad family of related tools repeatedly β€’ **Lazy Domain Initialization**: Handler classes instantiated via Proxy on first invocation, not during startup β€’ **Domain Self-Discovery**: Runtime manifest scanning ( ) replaces hardcoded imports; add new domains by creating a single manifest file β€’ **B-Skeleton Contracts**: Extensibility contracts for plugins ( ), workflows ( ), and observability ( ) β€’ **Context Efficiency Benchmark**: Built-in tool-schema init delta (Claude server-side count): β‰ˆ 3,000 tokens vs β‰ˆ 40,000+ tokens (10+ vs 290+ built-in tools; values change as tools/descriptions evolve) Tool Domains The server provides **290+ built-in tools** across **17+ domains** ( , , , , , , , , , , , , , , , , and ). > **View the complete Tool Reference β†—** Project Stats Star History