Cutter (Reverse Engineering) MCP server

cutterMCP is a Model Context Protocol server that enables Large Language Models (LLMs) to autonomously reverse engineer applications. It exposes core Cutter functionality through the MCP interface, allowing AI models to decompile and analyze binaries, rename methods and data, and list methods, imports, and exports.

Installation Requirements

Prerequisites

• Cutter application installed on your system
• Python 3
• MCP SDK

Setting Up cutterMCP

Installing the Cutter Plugin

1. Download the latest release from the cutterMCP repository
2. Launch Cutter
3. Navigate to Edit → Preferences → Plugins
4. Locate the plugin directory
5. Copy CutterMCPPlugin.py from the downloaded release
6. Paste it into the python folder inside the plugins directory
7. Restart Cutter
8. Verify installation by checking if the plugin appears under Windows → Plugins and as a new widget in the bottom panel

Connecting MCP Clients

cutterMCP is compatible with any MCP client. Below is an example for configuring Claude Desktop.

Setting Up Claude Desktop

To configure Claude Desktop as a Cutter MCP client:

1. Open Claude Desktop
2. Navigate to Claude → Settings → Developer → Edit Config → claude_desktop_config.json
3. Add the following configuration:

For MacOS/Linux:

{
  "mcpServers": {
    "cutter": {
      "command": "python",
      "args": [
        "/ABSOLUTE_PATH_TO/bridge_mcp_cutter.py"
      ]
    }
  }
}

For Windows:

{
  "mcpServers": {
    "cutter": {
      "command": "python",
      "args": [
        "C:\\ABSOLUTE_PATH_TO\\bridge_mcp_cutter.py"
      ]
    }
  }
}

Usage

Once installed and connected to an MCP client, the LLM can use cutterMCP to perform various reverse engineering tasks:

• Decompile binary files
• Analyze code structure
• Automatically rename methods and variables
• List methods, imports, and exports from the binary

With this integration, LLMs gain the ability to autonomously analyze binary files and provide insights through the Cutter reverse engineering platform.

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.