# JADX Android Decompiler

> Use this tool when you need to decompile and analyze Android code programmatically, navigating classes, methods, and fields through a structured API. It solves problems in reverse engineering by automating tasks, such as extracting call graphs, auto-documenting code, and searching for suspicious patterns. The tool takes in compiled Android code and outputs a structured representation of the decompiled codebase, making it ideal for use cases involving AI-driven analysis and automation.

Canonical page: https://skillsregistry.net/skills/mobilehackinglab-jadx-android-decompiler  
JSON: https://api.skillsregistry.net/v1/skills/mobilehackinglab-jadx-android-decompiler

## Description

The jadx-mcp-plugin is a powerful extension for the popular Jadx decompiler that exposes the internal decompiled code structure through the Model Context Protocol (MCP) — a structured API designed to facilitate programmatic access and interaction with the decompiled codebase.

This plugin transforms Jadx into an AI-friendly analysis environment, making it easier to:

Navigate code programmatically: AI tools and scripts can query classes, methods, and fields using structured requests, removing the need for brittle regex-based parsing.

Automate analysis tasks: Streamline repetitive reverse engineering workflows by integrating AI agents or scripts that can reason over the code and metadata.

Power intelligent reverse engineering: Combine with LLMs or AI frameworks to build automated code summarizers, vulnerability scanners, or Android deobfuscators.

🧠 Use Case in AI Reverse Engineering AI models, such as Claude, GPT-40 or domain-specific agents, can use the MCP API to:

Extract call graphs or class hierarchies for architectural analysis.

Auto-document code by interpreting class roles and method behaviors.

Search and highlight suspicious patterns (e.g., dynamic loading, reflection).

🧠 𝗡𝗼𝘄 𝘆𝗼𝘂 𝗰𝗮𝗻 𝗮𝘀𝗸 𝗖𝗹𝗮𝘂𝗱𝗲 𝘁𝗵𝗶𝗻𝗴𝘀 𝗹𝗶𝗸𝗲:
- "𝑆𝑒𝑎𝑟𝑐ℎ 𝑎𝑙𝑙 𝐽𝑎𝑣𝑎 𝐶𝑙𝑎𝑠𝑠𝑒𝑠 𝑡ℎ𝑎𝑡 ℎ𝑎𝑛𝑑𝑙𝑒 𝑢𝑠𝑒𝑟 𝑐𝑜𝑛𝑡𝑟𝑜𝑙𝑙𝑒𝑑 𝑖𝑛𝑝𝑢𝑡 𝑡ℎ𝑎𝑡 𝑙𝑒𝑎𝑑 𝑡𝑜 𝑝𝑎𝑡ℎ 𝑡𝑟𝑎𝑣𝑒𝑟𝑠𝑎𝑙 𝑖𝑠𝑠𝑢𝑒𝑠"

- "𝑆𝑒𝑎𝑟𝑐ℎ 𝑎𝑙𝑙 𝐽𝑎𝑣𝑎 𝐶𝑙𝑎𝑠𝑠𝑒𝑠 𝑡ℎ𝑎𝑡 ℎ𝑎𝑛𝑑𝑙𝑒 𝑢𝑠𝑒𝑟 𝑖𝑛𝑝𝑢𝑡 𝑡ℎ𝑎𝑡 𝑟𝑒𝑎𝑐ℎ 𝐽𝑁𝐼 𝑛𝑎𝑡𝑖𝑣𝑒 𝑐𝑎𝑙𝑙𝑠 𝑤𝑖𝑡ℎ 𝑢𝑠𝑒𝑟 𝑐𝑜𝑛𝑡𝑟𝑜𝑙𝑙𝑒𝑑 𝑖𝑛𝑝𝑢𝑡 𝑎𝑛𝑑 𝑓𝑖𝑛𝑑 𝑒𝑥𝑝𝑙𝑜𝑖𝑡𝑎𝑏𝑙𝑒 𝑣𝑢𝑙𝑛𝑒𝑟𝑎𝑏𝑖𝑙𝑖𝑡𝑖𝑒𝑠"

- "𝐶𝑟𝑒𝑎𝑡𝑒 𝑎 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛 𝑐𝑎𝑙𝑙 𝑔𝑟𝑎𝑝ℎ 𝑠ℎ𝑜𝑤𝑖𝑛𝑔 𝑡ℎ𝑒 𝑣𝑢𝑙𝑛𝑒𝑟𝑎𝑏𝑖𝑙𝑖𝑡𝑖𝑒𝑠"

Whether you're building a smarter reverse engineering assistant or just want more structured control over Jadx outputs, jadx-mcp-plugin is your gateway to the future of AI-augmented reverse engineering.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mobilehackinglab-jadx-android-decompiler)
- **Repository:** <https://github.com/mobilehackinglab/jadx-mcp-plugin>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "mobilehackinglab-jadx-android-decompiler"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mobilehackinglab-jadx-android-decompiler` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mobilehackinglab-jadx-android-decompiler/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
