x64dbg MCP server

The x64dbg MCP server implements the Model Context Protocol, allowing you to bridge large language models like Claude with the x64dbg debugger. This powerful integration enables you to control debugging operations through natural language prompts, making complex debugging tasks more accessible.

Installation

Plugin Setup

1. Download the appropriate plugin file for your debugger version:

   • .dp64 for x64dbg
   • .dp32 for x32dbg

2. Copy the plugin file to your x64dbg plugins directory:

   [x64dbg_installation_directory]/release/x64/plugins/
   

3. Launch x64dbg and verify that the plugin loaded correctly by checking the logs (press ALT+L).

Configuring Claude Desktop

1. Copy the x64dbgmcp.py file from the source directory to a location on your computer.

2. Update your claude_desktop_config.json to include the path to the Python script:

   {
     "mcpServers": {
       "x64dbg": {
         "command": "Path\\To\\Python",
         "args": [
           "Path\\to\\x64dbgmcp.py"
         ]
       }
     }
   }
   

3. Start Claude Desktop after launching x64dbg to establish the connection.

Using the MCP Server

Basic Commands

Once connected, you can interact with x64dbg using natural language prompts:

Setting Breakpoints

You can set breakpoints using simple language commands:

Set a breakpoint at the main function and step through the first few instructions

Memory Analysis

Examine memory contents with commands like:

Read 100 bytes from address 0x401000 and show me what's there

Register Inspection

Check register values easily:

What's the current value of RAX and RIP registers?

Pattern Searching

Find byte patterns in memory:

Find the pattern '48 8B 05' in the current module

Advanced Usage

API Mode

For faster debugging and more extensive tool chain calls, you can run the MCP server directly from the command line:

python x64dbgmcp.py [API_KEY] [MAX_TOOL_CALLS] [PORT]

Where:

• API_KEY is your Claude API key
• MAX_TOOL_CALLS sets the limit for consecutive tool calls
• PORT is optional - use this if the default port doesn't connect

Tips for Effective Use

1. Provide Binary Context: Always inform the model about the full path of your executable to enable restart capabilities:

   init C:\Absolute\Path\to\EXE
   

2. Check Connection Issues: If you have trouble connecting to the x64dbg session from the Python file, open the logs tab in x64dbg (ALT+L) to view the port the plugin is running on, then add that port as an argument to your Python script.

3. Tool Availability: The integration provides access to over 40 x64dbg SDK tools, supporting comprehensive debugging capabilities through natural language.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "x64dbg" '{"command":"Path\\To\\Python","args":["Path\\to\\x64dbg.py"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "x64dbg": {
            "command": "Path\\To\\Python",
            "args": [
                "Path\\to\\x64dbg.py"
            ]
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "x64dbg": {
            "command": "Path\\To\\Python",
            "args": [
                "Path\\to\\x64dbg.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect