How to analyze an Android APK with AI assistance using JADX
When to use: You have an APK to analyze and want AI to help understand its behavior.
Prerequisites
- JADX with jadx-ai-mcp plugin — jadx plugins --install 'github:zinja-coder:jadx-ai-mcp'
- JADX MCP Server running — Set up the Python MCP server with uv
Flow
-
Check the manifestGet the AndroidManifest.xml. What permissions does this app request and what components (activities, services, receivers) does it declare?✓ Copied→ Parsed manifest with permission analysis
-
Find interesting classesSearch for classes related to network communication or encryption. List them with their methods.✓ Copied→ Filtered class list with method signatures
-
Analyze and renameGet the source code of the main network class. Rename obfuscated methods to descriptive names based on their behavior.✓ Copied→ Decompiled code with meaningful names applied
Outcome: An annotated view of the APK with key functionality understood and obfuscation partially reversed.
Pitfalls
- Heavily obfuscated apps resist decompilation — Use get_smali_of_class for bytecode-level analysis when decompilation fails