What runtime dependencies does JADX-AI-MCP require?
Java 11+ and Python 3.10+ are required; the plugin runs inside JADX and the MCP Server is a Python process.
@zinja-coder
基本信息
Plugin for JADX to integrate MCP server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"jadx-ai-mcp": {
"command": "uv",
"args": [
"venv"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
JADX-AI-MCP is a plugin for the JADX decompiler that integrates with Model Context Protocol (MCP) to enable real-time reverse engineering of Android APKs using LLMs like Claude. It provides live “Decompile → Context-Aware Code Review → AI Recommendations” capability.
Download both the jadx-ai-mcp-<version>.jar plugin and the jadx-mcp-server-<version>.zip from the releases page, then run the JADX-AI-MCP plugin inside JADX and the standalone JADX MCP Server to enable MCP tool communication.
Java 11+ and Python 3.10+ are required; the plugin runs inside JADX and the MCP Server is a Python process.
The JADX MCP Server (Python) receives MCP tool invocations from an LLM client, forwards them via HTTP to the JADX-AI-MCP plugin inside JADX, and returns the response.
Yes. It includes tools to rename classes, methods, fields, packages, and variables within the JADX decompilation session.
It can fetch AndroidManifest.xml content, strings.xml, resource file names and content, main activity class, application classes, and smali of any class.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
🚀 The fast, Pythonic way to build MCP servers and clients.
Open-source MCP to use Blender with any LLM

Model Context Protocol Servers
A search tool helps dev to solve the naming things problem.
评论