🕵️‍♂️ JNISleuth-MCP

Bridge the Java-to-Native Chasm in Android Reverse Engineering.
Automated RegisterNatives Recovery, Stripped ARM64 .so Type Reconstruction, and a Unified Jadx + Ghidra or IDA MCP Server for AI-Assisted Malware Analysis.

Quickstart • How It Works • MCP Tools • Stealth Dobby Agent • Roadmap

⚡ Why JNISleuth-MCP?

Modern Android malware, banking trojans, spyware, and commercial packers hide their core logic (C2 encryption, key derivation, environment checks, and exploit routines) inside stripped C/C++ native libraries (lib*.so).

When reversing across the JNI boundary, analysts hit three walls:

1. Broken Cross-References: native methods declared in classes.dex do not use standard Java_com_pkg_Class_method symbols. Instead, they are dynamically bound at runtime inside an obfuscated JNI_OnLoad via JNIEnv->RegisterNatives().

2. Blind Decompilation: Opening a stripped .so in Ghidra or IDA shows thousands of unnamed sub_XXXX functions where JNIEnv* vtable calls look like raw pointer arithmetic ((**(code **)(*param_1 + 0x538))(param_1, param_2)).

3. Disconnected AI Context: Existing Ghidra MCP and Jadx MCP servers live in silos—an LLM cannot trace data flow from an Android BroadcastReceiver in Java straight into an ARM64 encryption routine in libnative-lib.so.

JNISleuth-MCP eliminates the context switch. It automatically recovers static and dynamic RegisterNatives bindings, re-types stripped ARM64 functions in Ghidra, and exposes a single unified Model Context Protocol (MCP) server connecting DEX bytecode to native assembly.

Related MCP server: Frida Agent MCP

🏗️ Architecture & How It Works

flowchart LR
    subgraph Input["📦 Target APK / Malware"]
        DEX["classes*.dex"]
        ELF["Stripped lib/*.so (ARM64)"]
    end

    subgraph Harvester["🔍 Stage 1: JNI Bridge Harvester"]
        StaticScan["Static ELF & DEX Scanner\n(LIEF + Capstone + Heuristic Triplets)"]
        DobbyAgent["Stealth Native Agent\n(C++ / NDK / Dobby Inline Hook)"]
    end

    subgraph GhidraEngine["⚙️ Stage 2: Ghidra Headless Reconstructor"]
        Renamer["Function Renamer & Signature Applier"]
        VTable["JNIEnv* VTable & Struct Propagator"]
    end

    subgraph MCPServer["🤖 Stage 3: Unified FastMCP Server"]
        CrossGraph["Cross-Boundary Callgraph\n(Jadx Java + Ghidra C/ARM64)"]
        CallbackTrace["Upcall Tracer\n(Native -> Java Reflection)"]
    end

    DEX --> StaticScan
    ELF --> StaticScan
    ELF -. "Packed / OLLVM?" .-> DobbyAgent
    StaticScan --> Renamer
    DobbyAgent -- "register_natives.json" --> Renamer
    Renamer --> VTable
    VTable --> CrossGraph
    VTable --> CallbackTrace

🎬 See It In Action

1. CLI Static + Dynamic RegisterNatives Recovery

Run jnisleuth scan against an APK with stripped native libraries:

$ jnisleuth scan --apk samples/banker_dropper.apk --arch arm64-v8a

[*] Parsing 3 DEX files... Found 14 declared `native` methods across 4 classes.
[*] Inspecting lib/arm64-v8a/libcore-crypto.so (Stripped ELF, 0 exported Java_* symbols)
[*] Running static JNINativeMethod triplet scanner on .rodata / .data.rel.ro...
    [+] Resolved 11/14 methods via static struct table @ 0x0004d210
[!] 3 methods unresolved (constructed dynamically on stack in JNI_OnLoad).
[*] Launching headless Dobby collector on device (emulator-5554)...

┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┓
┃ Java Class & Method                      ┃ JNI Signature        ┃ .so Offset (ARM64)  ┃ Resolution Mode  ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━┩
│ com.dropper.Core#initEngine              │ (Landroid/content/.. │ libcore.so+0x001a40 │ Static (.rodata) │
│ com.dropper.Core#decryptPayload          │ ([BLjava/lang/Stri.. │ libcore.so+0x0023c8 │ Static (.rodata) │
│ com.dropper.Core#signC2Beacon            │ (Ljava/lang/String.. │ libcore.so+0x003f10 │ Dynamic (Dobby)  │
│ com.dropper.net.SocketBridge#connectRaw  │ (Ljava/lang/String.. │ libcore.so+0x004890 │ Dynamic (Dobby)  │
└──────────────────────────────────────────┴──────────────────────┴─────────────────────┴──────────────────┘
[+] Synced 14 function signatures and JNIEnv* types to Ghidra project: banker_dropper.gpr

2. Before vs. After in Ghidra

Before JNISleuth-MCP (FUN_000123c8):

long FUN_000123c8(long *param_1, undefined8 param_2, undefined8 param_3, undefined8 param_4) {
  char *pcVar1;
  long lVar2;
  pcVar1 = (char *)(**(code **)(*param_1 + 0x548))(param_1, param_4, 0);
  lVar2 = (**(code **)(*param_1 + 0x5c0))(param_1, param_3, 0);
  sub_00014a00(lVar2, pcVar1);
  (**(code **)(*param_1 + 0x550))(param_1, param_4, pcVar1);
  return param_3;
}

After JNISleuth-MCP (Java_com_dropper_Core_decryptPayload):

jbyteArray Java_com_dropper_Core_decryptPayload(
    JNIEnv *env, jobject thiz, jbyteArray encryptedData, jstring rc4KeyStr) 
{
  const char *key_utf = (*env)->GetStringUTFChars(env, rc4KeyStr, NULL);
  jbyte *payload_bytes = (*env)->GetByteArrayElements(env, encryptedData, NULL);
  rc4_crypt_buffer(payload_bytes, key_utf);
  (*env)->ReleaseStringUTFChars(env, rc4KeyStr, key_utf);
  return encryptedData;
}

🤖 Universal LLM & MCP Support (Works With Any Model)

JNISleuth-MCP is 100% model-agnostic. You can connect it to any cloud or local LLM via the standard Model Context Protocol (stdio JSON-RPC 2.0) or export native OpenAI / Gemini / Ollama function-calling schemas:

• Cloud LLMs & Agents: Google Gemini CLI, OpenAI / ChatGPT Desktop / Codex CLI, Cursor, Windsurf, Cline, Roo Code, Claude Desktop / Claude Code

• Local / Self-Hosted LLMs: Ollama, vLLM, LM Studio, OpenWebUI, Continue.dev (DeepSeek-R1, Qwen-2.5-Coder, Llama-3.3)

• Custom Python Agent SDKs: Direct tool-schema export (jnisleuth llm-tools --format openai|gemini|mcp) for LangChain, LlamaIndex, LiteLLM, OpenAI SDK, or google-genai.

🥷 Stealth Dobby Agent (Anti-RASP & Packer Mode)

Many wild Android malware families and commercial protectors immediately crash or exit if they detect frida-agent.so in /proc/self/maps, gum-js-loop threads, or modified function prologues in libc.so.

JNISleuth-MCP includes an optional zero-Frida native collector (agent-native/) written in C++20 and ARM64 assembly using Dobby:

• Mid-Function Hooking: Places hooks inside the ArtMethod::RegisterNative / JNIEnvExt::RegisterNatives dispatch path rather than the first instruction of exported stubs, evading basic prologue integrity scanners.

• Base-Address Normalization: Uses dladdr() and linker soinfo traversal to automatically subtract ASLR slide and record deterministic file offsets (libfoo.so + 0x23c8), even if the packer unmaps ELF section headers after JNI_OnLoad.

🚀 2-Minute Quickstart

Prerequisites

• Python 3.10+ (pip install uv)

• Ghidra 11.0+ (GHIDRA_INSTALL_DIR) or IDA Pro 9.0+ (IDA_INSTALL_DIR / idapyswitch)

• Jadx CLI installed in $PATH

• (Optional) Android NDK r26+ & ADB for dynamic Dobby collection

Installation

git clone https://github.com/<your-username>/JNISleuth-MCP.git
cd JNISleuth-MCP
uv sync

# 1. Scan the included obfuscated NDK crackme sample & sync with Ghidra / IDA Pro 9.0:
uv run jnisleuth scan --apk examples/obfuscated_jni_sample.apk --ghidra-headless --ida-headless

# 2. Resolve & patch OLLVM CSEL + BR X8 indirect branches in JNI_OnLoad:
uv run jnisleuth deobfuscate --so examples/libcore-crypto.so --offset 0x5200 --patch-out examples/libcore-crypto.deobf.so

Connect to Any LLM / IDE Agent (mcp.json / settings.json)

Works out of the box with Gemini CLI (~/.gemini/settings.json), Cursor (.cursor/mcp.json), Windsurf, Cline, Continue.dev (Ollama), ChatGPT Desktop, and Claude:

{
  "mcpServers": {
    "jnisleuth-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/JNISleuth-MCP", "jnisleuth-mcp"],
      "env": {
        "GHIDRA_INSTALL_DIR": "/opt/ghidra",
        "IDA_INSTALL_DIR": "/opt/idapro-9.0"
      }
    }
  }
}

Use with OpenAI / Gemini / Ollama Python SDKs Directly (No MCP Client Needed)

# Export function-calling tool schemas for OpenAI / Ollama / vLLM or Google Gemini:
uv run jnisleuth llm-tools --format openai > openai_tools.json
uv run jnisleuth llm-tools --format gemini > gemini_tools.json

🗺️ Roadmap

• Static DEX native method parser + ELF .rodata / .data.rel.ro JNINativeMethod triplet scanner

• Headless Ghidra JNIEnv* vtable auto-typing script for ARM64 & x86_64

• Unified FastMCP server bridging Jadx, Ghidra & IDA Pro 9.0

• On-device Dobby mid-function RegisterNatives + DexFile::OpenCommon unpacker module

• IDA Pro 9.0 (idapyswitch / idalib / headless idat64) backend support alongside Ghidra

• Automated OLLVM indirect-branch (BR X8) resolver & ELF patcher for JNI_OnLoad state machines

⚠️ Disclaimer

JNISleuth-MCP is developed for defensive malware analysis, mobile application security assessments, and reverse-engineering research. All sample binaries in examples/ are synthetic crackmes created specifically for testing.