ランキングに戻る

vmoranv/jshookmcp

TypeScriptvmoranv.github.io/jshookmcp/

js hook toolkit that all you need

browser-automationdebuggingdeobfuscationjs-reversemcpnetwork-analysisreverse-engineeringsecurity-analysis
スター成長
スター
1.8k
フォーク
432
週間成長
Issue
0
5001k1.5k
26年2月26年3月26年5月26年7月
成果物npmnpm install jshookmcp
README

@jshookmcp/jshook

License: AGPLv3 Node.js 22.12+ TypeScript MCP pnpm

English | 中文

An MCP server that gives AI agents 600+ tools across 34 domains for JavaScript analysis and security research — browser automation, CDP debugging, network interception, JS hooks, LLM-powered code analysis, process/memory forensics, WASM reverse engineering, source-map reconstruction, AST transforms, and composite workflows in a single server.

🚀 Quick Start

No global install needed — add to your MCP client config and you're ready:

Claude Desktop / Cursor (claude_desktop_config.json):

{
  "mcpServers": {
    "jshook": {
      "command": "npx",
      "args": ["-y", "@jshookmcp/jshook@latest"],
      "env": { "JSHOOK_BASE_PROFILE": "search" }
    }
  }
}

(Windows: use npx.cmd absolute path if npx is not found)

Share one daemon across multiple agents

The default stdio configuration starts one full jshook process per MCP host. To share the embedding model, browser runtime, and caches, start one local Streamable HTTP daemon:

pnpm build
pnpm daemon

Then point every MCP client at http://127.0.0.1:3000/mcp using its HTTP/URL server configuration. Each client receives its own MCP session and response route while heavyweight runtime resources remain in one process. Keep the default loopback bind; set MCP_AUTH_TOKEN before exposing the endpoint beyond localhost.

🌟 Highlights

  • 🤖 AI-Driven Analysis — LLM-powered deobfuscation, crypto detection, AST comprehension
  • Search-First Context Efficiencysearch profile ≈ 3K tokens vs full ≈ 40K+ tokens
  • 🎯 Progressive Tierssearchworkflowfull, activate on demand
  • 🌐 Full-Stack Browser Automation — Chromium/Camoufox + CDP + anti-detection + CAPTCHA handling
  • 🔁 Runtime Recovery and Session Isolation — HTTP sessions restore activated domains, browser attach state, coverage state, and isolate browser-side session state per client
  • 🧭 Schema-First Meta Toolsdescribe_tool, validated call_tool, and coverage_report reduce parameter errors and make tool coverage visible
  • 📡 Network Interception — HTTP/2 frame building, MiTM capture, GraphQL, Burp Suite bridge
  • 🛠️ Reverse Engineering Toolchain — WASM disassembly, binary analysis, Frida, Ghidra/IDA bridges
  • 🧰 Process & Memory Forensics — Native FFI scanning, hardware breakpoints, PE introspection
  • 🧩 Dynamic Extensibility — Hot-reload plugins, declarative workflows, auto-discovered domains

Recent Runtime Notes

  • HTTP transport now multiplexes independent MCP sessions and restores runtime state after reconnects.
  • proxy_start auto-generates a local HTTPS interception CA when needed.
  • Browser CAPTCHA solving is now explicit-input driven: pass taskKind, siteKey, imageBase64, callbackName, and responseSelector as needed. Built-in widget/page signature probing is intentionally not used.

Architecture

  • Runtime Registry — Domains auto-discovered via manifest.ts; add a domain by creating one file
  • Lazy Initialization — Handlers instantiated on first call, not at startup
  • BM25 + Vector Searchsearch_tools meta-tool with hybrid ranking and adaptive weights
  • MCP ToolAnnotations — Every tool carries readOnlyHint / destructiveHint / idempotentHint / openWorldHint

Registry Snapshot

The built-in surface below is generated from the runtime registry and checked in CI.

  • Package version: 0.3.4
  • Built-in Tools: 636
  • Domains: adb-bridge, binary-instrument, boringssl-inspector, browser, canvas, coordination, core, cross-domain, dart-inspector, debugger, encoding, exploit-dev, extension-registry, graphql, instrumentation, maintenance, memory, mojo-ipc, native-bridge, native-emulator, network, platform, process, protocol-analysis, proxy, sourcemap, streaming, syscall-hook, trace, transform, v8-inspector, wasm, webgpu, workflow
  • Note: this snapshot is generated from the runtime registry; do not edit the counts by hand.

View the complete Tool Reference ↗

Project Stats

関連リポジトリ
browser-use/browser-use

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

PythonPyPIMIT Licensellmai-agents
browser-use.com
106k11.7k
lightpanda-io/browser

Lightpanda: the headless browser designed for AI and automation

ZigGNU Affero General Public License v3.0browsercdp
lightpanda.io
32.1k1.4k
CloakHQ/CloakBrowser

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.

PythonPyPIMIT Licenseanti-detectbot-detection
cloakbrowser.dev
28.9k2.3k
alibaba/page-agent

JavaScript in-page GUI agent. Control web interfaces with natural language.

TypeScriptnpmMIT Licenseagentai
alibaba.github.io/page-agent/
27.4k2.4k
jackwener/OpenCLI

Make Any Website into CLI & Use your logged-in browser by AI agent.

JavaScriptnpmApache License 2.0ai-agentai-agents
opencli.info
27k2.7k
Skyvern-AI/skyvern

Automate browser based workflows with AI

PythonPyPIGNU Affero General Public License v3.0apiautomation
skyvern.com
22.5k2.1k
AutomaApp/automa

A browser extension for automating your browser by connecting blocks

VueOthervuechrome-extension
goautoma.com/extension
21.5k2.3k
h4ckf0r0day/obscura

The headless browser for AI agents and web scraping

Rustcrates.ioApache License 2.0antidetectantidetect-browser
obscura.sh
19.5k1.4k
getmaxun/maxun

🔥 The open-source no-code platform for web scraping, crawling, search and AI data extraction • Turn websites into structured APIs in minutes 🔥

TypeScriptnpmGNU Affero General Public License v3.0automationno-code
maxun.dev
16.7k1.4k
browser-use/web-ui

🖥️ Run AI Agent in your browser.

PythonPyPIMIT Licenseai-agentbrowser-automation
16.2k2.7k
browser-use/browser-harness

Browser Harness | Self-healing harness that enables LLMs to complete any task.

PythonPyPIMIT Licenseai-agentbrowser-agent
browser-harness.com
16.2k1.5k
lsdefine/GenericAgent

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

PythonPyPIMIT Licenseai-agentautomation
github.com/lsdefine/GenericAgent
13.5k1.6k