# zinja-coder/jadx-ai-mcp

Plugin for JADX to integrate MCP server

Repository: https://github.com/zinja-coder/jadx-ai-mcp
Canonical: https://ross.abutalabs.com/products/jadx-ai-mcp
Language: Java
License: Apache-2.0
License Family: permissive
Topics: ai, mcp-server, mobile, pentesting, reverse-engineering, sast, java, llm, mcp, mcp-servers, model-context-protocol, model-context-protocol-servers, vapt
Last push: 2026-08-06T15:56:52+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 96, longevity 36
- inputs: {"age_days": 513, "days_push": 27, "days_rel": 27, "gap_med": 6.0, "n_releases_24m": 29}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2711, forks 245 (observed 2026-08-28T04:07:11.832985+00:00)

## What it is
A JADX plugin that bundles an MCP server, allowing LLM clients like Claude to interact with the JADX decompiler for Android APK analysis. It enables AI-assisted reverse engineering, vulnerability discovery, and code analysis of decompiled Android apps.

## Use cases
- analyze android apk with claude
- ai-assisted reverse engineering of android apps
- find vulnerabilities in decompiled apk code
- connect jadx to an mcp-compatible llm client
- automate apk security analysis with llm
- decompile and inspect android app code with ai

## When to choose
- you already use JADX and want LLM-driven analysis of decompiled code
- you need AI-assisted APK reverse engineering or vulnerability hunting
- your MCP-capable client (e.g., Claude Desktop) should drive decompilation queries

## When to avoid
- you need to reverse engineer non-Android binaries
- you don't use JADX or any MCP-compatible LLM client
- you require fully offline analysis without an LLM

## Facets
- artifact type: plugin
- maturity: active
- function: mcp, reverse-engineering, security, llm-inference, plugin-system
- domain: reverse-engineering, security, mobile-development, large-language-models
- platform: jvm, cross-platform
- tags: jadx, android-apk-analysis, mcp-server, pentesting, sast, llm-integration, decompilation, ai-agents, desktop

## Member repositories
- zinja-coder/jadx-ai-mcp (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.832985+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:15:35.572739+00:00, confidence not recorded.
  - readme: https://github.com/zinja-coder/jadx-ai-mcp (fetched 2026-08-28T04:07:11.832985+00:00, sha 2d794523cfe2)
- Data as of 2026-08-30T08:39:29.467469+00:00.
