A JADX plugin and MCP server for analyzing Android APKs with LLMs like Claude.
jadx-ai-mcp is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view zinja-coder/jadx-ai-mcp --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
This tool connects JADX, a decompiler for Android apps, to AI models through the Model Context Protocol. It lets you ask questions about an app's code in plain English and get answers about vulnerabilities or how the app works.
JADX-AI-MCP is a plugin for JADX (a popular Android decompiler) that integrates a Model Context Protocol (MCP) server. It allows large language models (LLMs) like Claude to interact with JADX, enabling automated analysis of Android APKs. Users can ask natural language questions about decompiled code, identify security vulnerabilities, and perform reverse engineering tasks. The project includes both a JADX plugin and a standalone MCP server, making it easy to set up and use with various MCP-compatible AI agents. It supports Java 11+ and Python 3.10+.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 60 days ago.
2256 GitHub stars indicate community interest.
3 open issues signal maintenance load.
Apache-2.0 license detected.
Automated vulnerability assessment of Android APKs using AI.
Reverse engineering Android apps with natural language queries.
Integrating AI-powered code analysis into security workflows.
Teaching and learning Android app security through interactive Q&A.
Rapid triage of decompiled code for penetration testing.
Running AI analysis on untrusted APKs may expose sensitive data to the AI model if not properly sandboxed.
The MCP server listens on localhost; ensure it is not exposed to untrusted networks.
2,256
Stars
216
Forks
3
Issues
Apache-2.0
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
A JADX plugin and MCP server for analyzing Android APKs with LLMs like Claude.
Mobile security researchers and penetration testers., Reverse engineers analyzing Android applications., Developers building AI-assisted security tools.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Running AI analysis on untrusted APKs may expose sensitive data to the AI model if not properly sandboxed. The MCP server listens on localhost; ensure it is not exposed to untrusted networks.
Similar or complementary options to evaluate include roam-code, code-memory, MCP Server Collection.
Jun 6, 2026
2 security/trust notes recorded.
Setup difficulty is 3/5.