x64dbg MCP server

An MCP (Model Context Protocol) server for x64dbg allows you to interact with the x64dbg debugger through Large Language Models like Claude. This plugin enables dynamic analysis by providing an interface between the debugger and AI assistants, letting you control x64dbg through natural language.

Installation

Using Pre-built Files

1. Download the .dp64 file from the build\release directory
2. Move the file to your x64dbg plugins directory (typically yourx64dbginstalldir\release\x64\plugins)
3. Grab the x64dbgmcp.py file from the src directory and configure it with your Claude Desktop installation
4. Start x64dbg, then start Claude Desktop
5. Verify successful loading by checking the logs (press ALT+L in x64dbg)

Building from Source

If you need to build the plugin yourself:

git clone <repository-url>
cd build
cmake .. -DBUILD_X64=ON
cmake build . --config Release

Functionality

The current implementation supports four core x64dbg functions:

1. DbgCmdExec - Execute debugger commands
2. DbgIsActive - Check if a debugging session is active
3. GetModuleList - Retrieve loaded modules
4. FindMemBaseAddr - Find memory base addresses

Compatibility Note

This plugin currently supports x64dbg only. For x86 support, you'll need to build the plugin yourself with appropriate configuration.

Usage

After installation, the plugin creates an MCP server that allows Claude or other LLMs to interact with x64dbg. The communication happens through the Python script that connects to both the debugger and the AI assistant.

To use the plugin:

1. Start x64dbg
2. Load your target executable or attach to a process
3. Start Claude Desktop
4. Use natural language to instruct Claude to perform debugging operations

Example Operations

You can ask the AI assistant to:

• Execute debugger commands
• Check the active state of the debugger
• List loaded modules
• Find memory addresses

The plugin handles translating these requests into appropriate x64dbg operations through the MCP protocol.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.