JsHookMcp
@jshookmcp/jshook
English | 中文
这是一个 MCP (Model Context Protocol) 服务器,提供了一个由运行时注册表驱动的内置工具目录,用于 AI 辅助的 JavaScript 分析和安全分析。它将浏览器自动化、Chrome DevTools 协议调试、网络监控、智能 JavaScript 钩子、LLM 驱动的代码分析、进程和内存检查、WASM 工具、源码映射(source-map)重建、AST 转换以及复合工作流集成在单个服务器中。
文档 / 快速链接
Related MCP server: JS Reverse Strong MCP
🚀 快速开始
无需全局安装,即可在 Claude Desktop 或 Cursor 中立即使用 jshookmcp。
Claude Desktop 配置 (claude_desktop_config.json):
{
"mcpServers": {
"jshook": {
"command": "npx",
"args": ["-y", "@jshookmcp/jshook@latest"],
"env": {
"JSHOOK_BASE_PROFILE": "search"
}
}
}
}(Windows 用户注意:如果找不到 npx,请指定 npx.cmd 的绝对路径)
🌟 主要亮点
🤖 AI 驱动的分析:利用 LLM 进行智能 JavaScript 反混淆、加密算法检测和 AST 级别的代码理解。
⚡ 搜索优先的上下文效率:基于 BM25 的
search_tools+ 动态增强,将 jshook 的工具模式初始化增量从约 40.0K+ tokens (full) 降低至约 3.0K (search)(Claude 服务器端计数;不包含 Claude Code 基础提示词)。🎯 渐进式能力分层:内置三种配置文件 (
search/workflow/full),其中search作为按需扩展能力的默认基础层。🌐 全栈自动化:将 Chromium/Camoufox 浏览器、CDP 调试和网络拦截无缝编排为原子操作。
🛡️ 高级反调试:内置针对 debugger 语句、时间检查和严格的无头机器人指纹识别技术的规避手段。
🧩 动态扩展性:无需重新编译核心服务器,即可从本地目录热重载插件和工作流。
🔧 零接线扩展性:通过
manifest.ts自动发现域、延迟处理程序实例化,以及插件/工作流的 B-Skeleton 合约。🛠️ 逆向工程工具链:集成了 WASM 反汇编、二进制熵分析、内存扫描,以及 Burp Suite/Ghidra/IDA Pro 的桥接器。
🛡️ 核心能力
JSHookMCP 在 36 个领域提供了 360+ 个原子工具,为 AI 编排器提供了无与伦比的能力:
🕸️ 浏览器自动化与逆向工程:零配置 Chromium/Camoufox 注入、CDP (Chrome DevTools Protocol) 编排以及 iframe 评估绕过。
📡 网络拦截与欺骗:深度 HTTP/2 帧构建、MiTM 流量捕获、GraphQL 内省以及 Burp Suite 桥接。
🧠 AST 与语义分析:LLM 驱动的反混淆、WebAssembly (WASM) 反汇编、Source Map 重建以及二进制熵可视化。
🧰 进程与内存取证:原生 Frida 插桩、内存扫描、指针解引用以及严格的反调试缓解措施。
🔌 动态扩展性:可热重载的 B-Skeleton 插件和声明式
WorkflowContract流水线。
架构与性能
[!TIP] 上下文效率基准:内置工具模式初始化增量(Claude 服务器端计数):
search≈ 3.0K tokens vsfull≈ 40.0K+ tokens。
渐进式工具发现:
search_tools元工具 (BM25 排名) +activate_tools/activate_domain+ 基于配置文件的层级升级 (boost_profile)搜索层行为:
search_tools仅搜索并对结果进行排名;它不会自动运行activate_tools,也不会自动运行boost_profile。推荐链:search_tools -> activate_tools / activate_domain -> 仅在需要时使用 boost_profile不要为单个工具进行增强:
activate_tools可以从当前基础层跨层级注册精确工具;当您预期重复使用一系列相关的广泛工具时,boost_profile效果更好延迟域初始化:处理程序类在首次调用时通过 Proxy 实例化,而不是在启动时
域自发现:运行时清单扫描 (
domains/*/manifest.ts) 取代了硬编码导入;通过创建一个清单文件即可添加新域B-Skeleton 合约:插件 (
PluginContract)、工作流 (WorkflowContract) 和可观测性 (InstrumentationContract) 的扩展性合约MCP 工具注解:每个工具都带有语义注解 (
readOnlyHint,destructiveHint,idempotentHint,openWorldHint),使 AI 编排器能够在调用前推断工具的安全性和副作用
注册表快照
下方的内置表面由运行时注册表生成,并在 CI 中进行检查。
包版本:
0.3.0内置工具:
387域:
adb-bridge,antidebug,binary-instrument,boringssl-inspector,browser,canvas,coordination,core,cross-domain,debugger,encoding,evidence,extension-registry,graphql,hooks,instrumentation,macro,maintenance,memory,mojo-ipc,network,platform,process,protocol-analysis,proxy,sandbox,shared-state-board,skia-capture,sourcemap,streaming,syscall-hook,trace,transform,v8-inspector,wasm,workflow注意:此快照由运行时注册表生成;请勿手动编辑计数。
项目统计
Star 历史
Available Tools
8 toolsactivate_domainA
Register every tool in a single domain at once. Use this when a task needs a whole capability area; prefer search_tools or activate_tools when you only need a few specific tools, because activating a domain costs far more context. Domains: . Activated tools appear in the tool list immediately; if your client does not refresh its tool list, invoke them with call_tool. Activation draws on the session context budget: when the budget is full, least-recently-used tools are evicted to make room, and the response reports what was activated and what was evicted. Pass precheck: true to preview wouldActivate / wouldEvict without changing anything. Activated tools auto-deactivate after ttlMinutes (default 30; pass 0 for no expiry). Use reload_extensions first to include external plugin/workflow domains.
Inputs: domain (required), precheck, ttlMinutes.
activate_toolsA
Dynamically register specific tools by name, regardless of current base tier. Use after search_tools to enable exactly the tools you need. In search-tier sessions this is usually enough; use activate_domain when you need every tool in a domain. Activated tools appear in the tool list immediately. If tools do not appear after activation, use call_tool to invoke them directly.
Inputs: names (required), precheck.
call_toolA
Execute an already-active tool by name. Use this when activate_tools/activate_domain registered a tool but your client did not refresh its tool list. Does not auto-activate inactive tools.
Inputs: name (required), args, arguments, parameters.
coverage_reportA
Report which tools have been called in the current runtime and which known tools remain uncalled. Loads all domains first so the uncalled list reflects the full tool catalog, not just currently active tools.
Inputs: no named parameters.
deactivate_toolsA
Remove previously activated tools to free context. Only affects dynamically activated tools (added via activate_tools, activate_domain, or extension activation), not base profile tools.
Inputs: names (required).
describe_toolA
Get detailed information about a specific tool, including its input schema. Use this to see the exact parameters a tool expects before calling it.
Inputs: name (required).
route_toolA
One-stop tool router: accepts a natural language task description, returns recommended tools and next actions. Automatically detects workflow patterns, recommends activation order, and provides example arguments. Use this instead of search_tools when you want guided tool discovery with actionable next steps.
Inputs: task (required), context.
search_toolsA
Search 736 tools across 36 capability domains. This includes built-in tools plus any loaded plugin/workflow tools (0 currently loaded). In search-tier sessions, call this before assuming a capability is unavailable. Use activate_tools for exact matches, activate_domain for an entire domain. Domains: browser (85) | memory (75) | native-emulator (57) | binary-instrument (46) | network (38) | process (29) | tls-inspector (29) | adb-bridge (26) | core (25) | debugger (21) | exploit-dev (21) | v8-inspector (21) | protocol-analysis (20) | platform (18) | maintenance (17) | streaming (17) | wasm (17) | dart-inspector (16) | syscall-hook (15) | instrumentation (13) | workflow (13) | coordination (12) | canvas (11) | proxy (11) | trace (10) | webgpu (10) | cross-domain (8) | mojo-ipc (8) | transform (8) | extension-registry (7) | graphql (7) | sourcemap (7) | native-bridge (6) | encoding (5) | tasks (4) | session (3). Query tip: before searching, distill your intent into key concepts (action verb + target + domain). The engine combines token matching, fuzzy names, profile context, and optional static embeddings.
Inputs: query (required), top_k, auto_activate.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Most tools have clearly distinct roles: discovery (search_tools, route_tool, describe_tool), activation lifecycle (activate_tools, activate_domain, deactivate_tools), execution (call_tool), and reporting (coverage_report). The only mild overlaps are search_tools vs route_tool (both discovery) and activate_tools vs activate_domain, but the descriptions explicitly differentiate them by intent and cost.
Nearly all names follow a consistent verb_noun snake_case pattern (search_tools, activate_tools, call_tool, describe_tool). The main deviation is coverage_report, which is a noun phrase rather than an action, but it remains readable and predictable.
Eight tools is well-scoped for a meta-server that manages 736 tools across 36 domains. Each tool covers a distinct phase of the discovery-activation-execution lifecycle and none feels redundant or filler.
The surface covers discovery, activation, deactivation, execution, and coverage reporting, but there is no dedicated tool to list currently active tools or enumerate domains, and activate_domain's domain list is empty. The descriptions also reference reload_extensions, which is not present in the tool set, creating a dead end for plugin/workflow domain loading.
Maintenance
Related MCP Connectors
Anonymous webhook capture, inspection, waiting, and response configuration for AI agents.
660+ data tools for agents: TikTok, Douyin, Instagram, YouTube, X, weather, GitHub. Pay per call.
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Discover, inspect and run 63,000+ agent tools from one balance. Pay per call, no subscriptions.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI coding assistants to debug and analyze JavaScript code in web pages through breakpoint debugging, function hooking, network analysis, and runtime inspection of scripts including minified code.241,064 npm3,072Apache 2.0
- AlicenseNot gradedqualityDmaintenanceStandardizes front-end JavaScript reverse engineering workflows by providing tools for browser observation, runtime sampling, hooking, debugging, network analysis, and local environment reproduction.74Apache 2.0
- FlicenseAqualityDmaintenanceChrome browser JS reverse engineering MCP tool for CTF/Web security, enabling dynamic analysis and restoration of login encryption logic.3120-
- AlicenseNot gradedqualityDmaintenanceA unified MCP server for JavaScript reverse engineering that provides full hook, breakpoints, script debugging, and browser automation with CDP anti-detection, supporting both ATTACH and LAUNCH modes.2Apache 2.0