JsHookMcp
@jshookmcp/jshook
Englisch | 中文
Ein MCP-Server (Model Context Protocol) mit einem laufzeit-registry-gesteuerten Katalog integrierter Tools für KI-gestützte JavaScript-Analyse und Sicherheitsanalyse. Er kombiniert Browser-Automatisierung, Chrome DevTools Protocol-Debugging, Netzwerküberwachung, intelligente JavaScript-Hooks, LLM-gestützte Codeanalyse, Prozess- und Speicherinspektion, WASM-Tools, Source-Map-Rekonstruktion, AST-Transformationen und zusammengesetzte Workflows in einem einzigen Server.
Dokumentation / Schnelllinks
Related MCP server: JS Reverse Strong MCP
🚀 Schnellstart
Verwenden Sie jshookmcp sofort mit Claude Desktop oder Cursor, ohne etwas global installieren zu müssen.
Claude Desktop-Konfiguration (claude_desktop_config.json):
{
"mcpServers": {
"jshook": {
"command": "npx",
"args": ["-y", "@jshookmcp/jshook@latest"],
"env": {
"JSHOOK_BASE_PROFILE": "search"
}
}
}
}(Hinweis für Windows-Benutzer: Wenn npx nicht gefunden wird, geben Sie den absoluten Pfad zu npx.cmd an)
🌟 Wichtige Highlights
🤖 KI-gestützte Analyse: Nutzen Sie LLMs für intelligente JavaScript-Deobfuskierung, Erkennung kryptografischer Algorithmen und Codeverständnis auf AST-Ebene.
⚡ Suchbasierte Kontexteffizienz: BM25-gestützte
search_tools+ dynamische Boosts reduzieren das Init-Delta des Tool-Schemas von jshook von ~40,0K+ Tokens (full) auf ~3,0K (search) (Claude serverseitige Zählung; exklusive Claude Code Basis-Prompt).🎯 Progressive Fähigkeitsstufen: Drei integrierte Profile (
search/workflow/full), wobeisearchals Standard-Basisstufe für bedarfsgerechte Skalierung der Fähigkeiten dient.🌐 Full-Stack-Automatisierung: Orchestrieren Sie nahtlos Chromium/Camoufox-Browser, CDP-Debugging und Netzwerk-Interception als atomare Aktionen.
🛡️ Fortgeschrittenes Anti-Debug: Integrierte Umgehung für Debugger-Statements, Timing-Prüfungen und strikte Headless-Bot-Fingerprinting-Techniken.
🧩 Dynamische Erweiterbarkeit: Laden Sie Plugins und Workflows zur Laufzeit aus lokalen Verzeichnissen neu, ohne den Kernserver neu kompilieren zu müssen.
🔧 Zero-Wiring-Erweiterbarkeit: Automatisch erkannte Domains via
manifest.ts, verzögerte Handler-Instanziierung und B-Skeleton-Verträge für Plugins/Workflows.🛠️ Reverse-Engineering-Toolchain: Integrierte WASM-Disassemblierung, binäre Entropieanalyse, Speicher-Scanning und Bridges für Burp Suite/Ghidra/IDA Pro.
🛡️ Kernfähigkeiten
JSHookMCP bietet über 360 atomare Tools in 36 Domains, die KI-Orchestratoren mit beispiellosen Fähigkeiten ausstatten:
🕸️ Browser-Automatisierung & Reverse Engineering: Zero-Config Chromium/Camoufox-Injektion, CDP-Orchestrierung (Chrome DevTools Protocol) und Umgehung von Iframe-Evaluierungen.
📡 Netzwerk-Interception & Spoofing: Tiefgreifende HTTP/2-Frame-Erstellung, MiTM-Traffic-Erfassung, GraphQL-Introspektion und Burp Suite-Bridge.
🧠 AST & Semantische Analyse: LLM-gestützte Deobfuskierung, WebAssembly (WASM)-Disassemblierung, Source-Map-Rekonstruktion und Visualisierung binärer Entropie.
🧰 Prozess- & Speicherforensik: Native Frida-Instrumentierung, Speicher-Scanning, Pointer-Dereferenzierung und strikte Anti-Debug-Mitigation.
🔌 Dynamische Erweiterbarkeit: Zur Laufzeit neu ladbare B-Skeleton-Plugins und deklarative
WorkflowContract-Pipelines.
Architektur & Leistung
[!TIP] Kontexteffizienz-Benchmark: Init-Delta des integrierten Tool-Schemas (Claude serverseitige Zählung):
search≈ 3,0K Tokens vsfull≈ 40,0K+ Tokens.
Progressive Tool-Erkennung:
search_toolsMeta-Tool (BM25-Ranking) +activate_tools/activate_domain+ profilbasierte Stufen-Upgrades (boost_profile)Verhalten der Suchstufe:
search_toolssucht und bewertet nur Ergebnisse; es führtactivate_toolsnicht automatisch aus und führtboost_profilenicht automatisch aus. Bevorzugte Kette:search_tools -> activate_tools / activate_domain -> boost_profile nur bei BedarfNicht für ein einzelnes Tool boosten:
activate_toolskann exakte Tools über Stufen hinweg von der aktuellen Basisstufe aus registrieren;boost_profileist besser, wenn Sie erwarten, eine breite Familie verwandter Tools wiederholt zu verwendenLazy Domain-Initialisierung: Handler-Klassen werden bei der ersten Verwendung via Proxy instanziiert, nicht beim Start
Domain-Selbsterkennung: Laufzeit-Manifest-Scanning (
domains/*/manifest.ts) ersetzt hartcodierte Importe; fügen Sie neue Domains durch Erstellen einer einzigen Manifest-Datei hinzuB-Skeleton-Verträge: Erweiterbarkeitsverträge für Plugins (
PluginContract), Workflows (WorkflowContract) und Beobachtbarkeit (InstrumentationContract)MCP ToolAnnotations: Jedes Tool enthält semantische Annotationen (
readOnlyHint,destructiveHint,idempotentHint,openWorldHint), die es KI-Orchestratoren ermöglichen, vor der Ausführung über die Sicherheit und Nebenwirkungen von Tools zu urteilen
Registry-Snapshot
Die unten aufgeführte integrierte Oberfläche wird aus der Laufzeit-Registry generiert und in der CI geprüft.
Paketversion:
0.3.0Integrierte Tools:
387Domains:
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,workflowHinweis: Dieser Snapshot wird aus der Laufzeit-Registry generiert; bearbeiten Sie die Zählungen nicht manuell.
Projektstatistiken
Star-Verlauf
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