X64dbg

x64dbg plugin project that enables dynamic analysis and LLM interaction through HTTP services

Developer tools Security #Debugging Plugin #Dynamic Analysis #LLM Interaction .cpp

rating : 2.5 points

downloads : 17

update time : 2025-04-28

What is x64dbgmcp?

x64dbgmcp is a plugin based on the Model Context Protocol (MCP) that allows users to interact with the x64dbg debugger through simple conversations, thus easily performing dynamic analysis tasks.

How to use x64dbgmcp?

Simply install the plugin and start a debugging session in x64dbg, then send instructions through the Claude Desktop client to start the analysis.

Applicable Scenarios

Suitable for software developers and security researchers who need to quickly locate program logic, check memory status, or monitor API calls.

Main Features

Support for Multiple InterfacesCurrently supports four core functional interfaces, and more functions are planned to be expanded in the future.

Cross - platform CompatibilityIt can run on different operating systems with only one build.

Advantages and Limitations

Advantages

Simplify the dynamic analysis process without manual operation

Support multiple programming languages and frameworks

Active community for continuous performance optimization

Limitations

The current version only supports partial functions

Depends on specific environment configuration

How to Use

Download and Install the Plugin

Clone the project repository from GitHub, compile to generate the plugin file and place it in the specified directory.

Start x64dbg and Claude Desktop

Ensure that both applications are running on the same machine and connected to the same network.

Usage Examples

Case Title: Check Module InformationGet all the modules loaded by the target process by sending a command.

Case Title: Set a Breakpoint and Track ExecutionSet a breakpoint and then continue to execute the program to observe its behavioral changes.

Frequently Asked Questions

How to confirm that the plugin has been successfully loaded?

Does it support the x86 architecture?

Related Resources

Official Documentation

Details all available API interfaces

GitHub Repository

Access the latest version and submit feedback

🚀 x64dbg MCP Protocol Plugin

This plugin enables dynamic analysis in x64dbg, allowing users to interact with the debugger as easily as having a conversation with a large - language model.

🚀 Quick Start

✨ Features

This plugin currently supports only four functions provided by the x64dbgSDK:

DbgCmdExec
DbgIsActive
GetModuleList
FindMemBaseAddr

This plugin is only suitable for x64dbg. If you need to use it for x86, please compile it yourself.

I aim to add most of the functions provided by the SDK, making dynamic analysis as simple as chatting with a large - language model. You can find the function links here.

Most of the HTTP server code was generated by Claude Sonnet 3.7. So, if the code seems overly complex, that's the reason.

This is my first repository, so I'm aware that I might have made some mistakes. Any suggestions or additional features are welcome.

📦 Installation

Simple Installation Steps

Obtain the .dp64 file from the build\release directory and move it to your defualtx64dbgdir\release\x64\plugins directory.
Get the x64dbgmcp.py file from the src directory and map your claude_desktop_config file to its installation location.
Start x64dbg, then start Claude Desktop. You can always check if the plugin is successfully loaded in x64dbg by pressing ALT + L.

Build Guide

Clone the repository.
Navigate to the build directory.
Execute the command: cmake .. -DBUILD_X64=ON
Execute the command: cmake build . --config Release

💻 Usage Examples

There is no specific code example provided in the original README. If you want to show how to use the functions supported by the plugin, you can add relevant code snippets here.

📚 Documentation

This section can be used to provide more detailed information about the plugin's functions, parameters, and usage scenarios.

🔧 Technical Details

There is no specific technical details provided in the original README. If you have more information about the implementation principle, algorithm, etc., you can add them here.