What is Binary Ninja MCP?

Binary Ninja MCP is a plugin and bridge system that integrates Binary Ninja (a powerful binary analysis and reverse engineering tool) with various MCP (LLM client) implementations, enabling AI-assisted reverse engineering workflows.

How to use Binary Ninja MCP?

1. Install Binary Ninja and the plugin through Binary Ninja's Plugin Manager or manually copy the repository.
2. For Claude Desktop integration, set up the virtual environment and configure MCP server settings.
3. Start the MCP server from Binary Ninja (Plugins > MCP Server > Start MCP Server).
4. Use your preferred MCP client (like Claude Desktop) to interact with Binary Ninja through natural language prompts.

Key features of Binary Ninja MCP?

• Real-time integration between Binary Ninja and MCP clients
• AI-assisted reverse engineering capabilities
• Extensive function coverage including:
  • Binary status checking
  • Function and data renaming
  • Code decompilation
  • Comment management
  • Type editing
  • Search capabilities
• Primary support for Claude Desktop with extensibility for other MCP clients

Use cases of Binary Ninja MCP?

1. Automated binary analysis report generation
2. Smart function renaming suggestions
3. AI-guided code decompilation reviews
4. Context-aware binary exploration
5. Quick function and data information retrieval
6. Collaborative reverse engineering sessions

FAQ from Binary Ninja MCP?

• **What are the system requirements?

  Binary Ninja, Python 3.12+, and Claude Desktop (or another MCP client)**

• Can I use this with other LLMs besides Claude?

  Yes, the MCP server can be used with other clients by implementing the appropriate integration layer.

• What programming knowledge is required?

  Basic Python knowledge for setup, but the interface is designed to be natural language-based.

• Is this free to use?

  The plugin is open-source (check the project's license), but you'll need a valid Binary Ninja license.

• What functions are currently supported?

  See the extensive list of supported integrations in the project documentation, including function listing, renaming, decompilation, and more.

Binary Ninja MCP

This repository contains a Binary Ninja plugin, MCP server, and bridge that enables seamless integration of Binary Ninja's capabilities with your favorite LLM client.

Features

• Seamless, real-time integration between Binary Ninja and MCP clients
• Enhanced reverse engineering workflow with AI assistance
• Primary support for Claude Desktop as the MCP client, but extensible for other integrations

Examples

Generating a Binary Analysis Report

Renaming Functions

Components

This repository contains two separate components:

1. A Binary Ninja plugin that provides an MCP server that exposes Binary Ninja's capabilities through HTTP endpoints. This can be used with any client that implements the MCP protocol.
2. A separate MCP bridge component that connects your favorite MCP client to the Binary Ninja MCP server. While Claude Desktop is the primary integration path, the MCP server can be used with other clients.

Supported Integrations

The following table details which integrations with Binary Ninja are currently supported.

Function	Description
get_binary_status	Get the current status of the loaded binary.
list_classes	List all namespace/class names in the program.
list_data_items	List defined data labels and their values.
list_exports	List exported functions/symbols.
list_imports	List imported symbols in the program.
list_methods	List all function names in the program.
list_namespaces	List all non-global namespaces in the program.
list_segments	List all memory segments in the program.
rename_data	Rename a data label at the specified address.
rename_function	Rename a function by its current name to a new user-defined name.
search_functions_by_name	Search for functions whose name contains the given substring.
decompile_function	Decompile a specific function by name and return the decompiled C code.
set_comment	Set a comment at a specific address.
set_function_comment	Set a comment for a function.
get_comment	Get the comment at a specific address.
get_function_comment	Get the comment for a function.
delete_comment	Delete the comment at a specific address.
delete_function_comment	Delete the comment for a function.
get_assembly_function	Get the assembly representation of a function by name or address.
function_at	Retrive the name of the function the address belongs to.
code_references	Retrive names and addresses of functions that call the given function.
get_user_defined_type	Retrive definition of a user defined type (struct, enumeration, typedef, union).
rename_variable	Rename variable inside a given function.
retype_variable	Retype variable inside a given function.
define_types	Add type definitions from a C string type definition.
edit_function_signature	Edit signature of a given function, given as a type string.

Prerequisites

• Binary Ninja
• Python 3.12+
• Claude Desktop (or your preferred integration)

Installation

Binary Ninja Plugin

You may install the plugin through Binary Ninja's Plugin Manager (Plugins > Manage Plugins).

To manually configure the plugin, this repository can be copied into the Binary Ninja plugins folder.

Claude Desktop Bridge (Optional)

This is only needed if you want to use Claude Desktop as your MCP client. Make sure that you have your virtual environment configured first:

git clone [email protected]:fosdickio/binary_ninja_mcp.git
cd binary_ninja_mcp

python3 -m venv .venv
source .venv/bin/activate   # On macOS/Linux

pip install -r bridge/requirements.txt

Automated Configuration (Mac)

On a Mac, you can automate the setup by running:

./scripts/setup_claude_desktop.py

Manual Configuration

On other operating systems or to manually configure the Claude Desktop integration:

1. Navigate to Settings > Developer > Edit Config
2. Add the following configuration:

{
  "mcpServers": {
    "binary_ninja_mcp": {
      "command": "/ABSOLUTE/PATH/TO/binary_ninja_mcp/.venv/bin/python",
      "args": [
        "/ABSOLUTE/PATH/TO/binary_ninja_mcp/bridge/binja_mcp_bridge.py"
      ]
    }
  }
}

Note: Replace /ABSOLUTE/PATH/TO with the actual absolute path to your project directory. The virtual environment's Python interpreter must be used to access the installed dependencies.

Usage

Claude Desktop

1. Open Binary Ninja and install the Binary Ninja MCP plugin
2. Restart Binary Ninja and then open a binary
3. Start the MCP server (Plugins > MCP Server > Start MCP Server)
4. Launch Claude Desktop

The integration will be automatically available after you open Claude Desktop.

You may now start prompting Claude about the currently open binary. Example prompts:

• "Generate a binary analysis report for the current binary."
• "Rename function X to Y in the current binary."
• "List all functions in the current binary."
• "What is the status of the loaded binary?"

Other MCP Client Integrations

The bridge can be used with other MCP clients by implementing the appropriate integration layer.

Development

The project structure is organized as follows:

binary_ninja_mcp/
├── bridge/                      # MCP client integration
├── plugin/                      # Binary Ninja plugin
├── scripts/
│   └── setup_claude_desktop.py  # Setup script for Claude Desktop

Contributing

Contributions are welcome. Please feel free to submit a pull request.