Djeb MCP Server
The MCP server of the JEB decompiler provides Android APK analysis functions for Claude Desktop, supporting reverse engineering operations such as decompilation, code navigation, and batch renaming.
rating : 2.5 points
downloads : 4.3K
What is JEB MCP Server?
JEB MCP Server is an innovative AI-assisted reverse engineering tool that builds a bridge between the JEB decompiler (a professional Android application analysis software) and Claude Desktop (Anthropic's AI assistant desktop application). With this tool, you can directly ask questions to Claude in natural language, and Claude can help you analyze Android applications, such as finding security vulnerabilities, understanding application functions, and extracting API interfaces, greatly simplifying the complex process of reverse engineering.How to use JEB MCP Server?
It's very simple to use: 1) Load your APK file in JEB and run the server script; 2) Configure Claude Desktop to connect to this server; 3) After restarting Claude, you can let Claude help you analyze the application just like having a chat. Claude will understand your needs, automatically call various analysis functions of JEB, and present the results in an easy-to-understand way.Use cases
This tool is particularly suitable for the following scenarios: security researchers analyzing application vulnerabilities, developers learning the implementation of excellent applications, beginners in reverse engineering lowering the learning threshold, enterprises conducting application security audits, and educational institutions for teaching demonstrations. Whether you are a professional security engineer or a novice interested in reverse engineering, you can benefit from it.Main Features
Intelligent Decompilation
Convert the DEX bytecode of an Android application into readable Java source code. It supports decompilation by method or by class, allowing you to easily view the internal logic of the application.
Code Navigation and Search
Quickly browse all classes, methods, and resource files in the application. It supports keyword search and regular expression matching, helping you quickly locate the content you're interested in.
Batch Renaming
Intelligently identify obfuscated class names, method names, and variable names, and rename them in batches to meaningful names, making the code easier to understand and analyze.
Resource File Analysis
Directly access and view AndroidManifest.xml, layout files, string resources, image resources, etc., to comprehensively understand the application configuration and interface structure.
Cross-Reference Tracing
Automatically find all usage locations of a certain method, field, or string in the application, helping you understand the code call relationship and data flow.
Class Inheritance Relationship Analysis
Visually display the class inheritance relationship and interface implementation, helping you understand the application architecture and design patterns.
Advantages
Greatly lower the threshold of reverse engineering without the need to memorize complex commands and operations.
Interact in natural language, just like having a conversation with an expert to analyze the application.
Combine AI intelligent understanding to provide context-related analysis suggestions.
Improve analysis efficiency and automate repetitive tasks.
Have a gentle learning curve, suitable for users with different levels of experience.
Limitations
Require a genuine license for the JEB decompiler.
Currently mainly support the analysis of Android APK files.
The understanding of AI may not be completely accurate and needs manual verification.
Network connection may affect the response speed.
The handling of particularly complex obfuscation may be limited.
How to Use
Environment Preparation
Ensure that you have installed the JEB decompiler (authorized version) and the Claude Desktop application. Download the code files of JEB MCP Server from GitHub.
Configure Claude Desktop
Edit the MCP configuration file of Claude Desktop and add the connection information of JEB MCP Server. The configuration file locations vary for different operating systems.
Start the JEB Server
Open the APK file you want to analyze in JEB, and then run the dJEB_mcp_server.py script through the script menu. The server will start in the background.
Start Using
Restart Claude Desktop. Now you can directly ask questions about APK analysis in Claude. Claude will automatically call the functions of JEB to answer you.
Usage Examples
Deep Link Analysis
Analyze how the application handles external links (such as opening from a browser or other applications), and find out all supported URL patterns and corresponding processing logic.
Intelligent Class Renaming
Rename obfuscated class names and method names to meaningful names, making intelligent inferences based on code functions, string constants, and usage patterns.
API Endpoint Extraction
Extract all network API interfaces from the application, including URLs, request methods, parameters, and response handling logic.
Broadcast Receiver Analysis
Analyze the broadcast receivers in the application to understand the events they listen to, the operations they perform, and their security status.
Execution Flow Tracing
Start from a certain entry point and trace the execution path of the code to understand the complete business process.
Frequently Asked Questions
Do I need to purchase a JEB license?
Is this tool safe? Will it leak my analysis data?
Which file formats are supported?
Is the analysis result of Claude accurate?
What should I do if I encounter connection problems?
Is this tool suitable for beginners in reverse engineering?
Related Resources
Model Context Protocol Official Documentation
Understand the technical details and design concepts of the MCP protocol.
JEB Decompiler Official Website
Get information about the JEB software and purchase a license.
GitHub Project Repository
Get the latest code, submit issues, and participate in development.
Claude Desktop Download
Download the Claude Desktop application.
Reverse Engineering Learning Resources
A collection of learning materials and tools related to reverse engineering.

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.5K
4.5 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
28.3K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
17.3K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
54.3K
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
24.0K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
51.9K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
18.1K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
35.4K
4.8 points