Kali Security Tools MCP server

This repository provides Model Context Protocol (MCP) servers specifically designed for Kali Linux environments, focusing on enhancing reverse engineering, security testing, and network analysis workflows. The MCP servers integrate various tools to help security professionals and developers streamline their tasks.

Installation

Prerequisites

• Kali Linux environment
• Docker (for sandbox support)
• Network analysis tools (Wireshark/tshark, Nmap)
• Binary analysis tools (nm, objdump, strings)

Basic Setup

1. Clone the repository:

   git clone https://github.com/username/awsome-kali-MCPServers.git
   cd awsome-kali-MCPServers
   

2. Install required dependencies:

   # Install basic dependencies
   sudo apt update
   sudo apt install -y nmap wireshark tshark binutils docker.io
   
   # Start Docker service
   sudo systemctl start docker
   sudo systemctl enable docker
   

Usage

Network Scanning with Nmap

The MCP server provides several network scanning functions:

# Example MCP client request
client.request("basic_scan", {"target": "192.168.1.0/24"})
client.request("intense_scan", {"target": "example.com"})
client.request("stealth_scan", {"target": "10.0.0.1"})
client.request("quick_scan", {"target": "172.16.0.1"})
client.request("vulnerability_scan", {"target": "192.168.1.10"})

Binary Analysis

Analyze binaries using various tools:

Symbol Analysis (nm)

client.request("basic_symbols", {"file": "/path/to/binary"})
client.request("dynamic_symbols", {"file": "/path/to/binary"})
client.request("demangle_symbols", {"file": "/path/to/binary"})
client.request("numeric_sort", {"file": "/path/to/binary"})
client.request("size_sort", {"file": "/path/to/binary"})
client.request("undefined_symbols", {"file": "/path/to/binary"})

Disassembly and Analysis (objdump)

client.request("file_headers", {"file": "/path/to/binary"})
client.request("disassemble", {"file": "/path/to/binary"})
client.request("symbol_table", {"file": "/path/to/binary"})
client.request("section_headers", {"file": "/path/to/binary"})
client.request("full_contents", {"file": "/path/to/binary"})

String Extraction

client.request("basic_strings", {"file": "/path/to/binary"})
client.request("min_length_strings", {"file": "/path/to/binary", "min_length": 10})
client.request("offset_strings", {"file": "/path/to/binary"})
client.request("encoding_strings", {"file": "/path/to/binary", "encoding": "utf-16"})

Network Traffic Analysis

Analyze network traffic using Wireshark/tshark:

# Capture live traffic
client.request("capture_live", {"interface": "eth0", "duration": 30})

# Analyze existing PCAP files
client.request("analyze_pcap", {"file": "/path/to/capture.pcap"})

# Extract HTTP data
client.request("extract_http", {"file": "/path/to/capture.pcap"})

# Get protocol hierarchy
client.request("protocol_hierarchy", {"file": "/path/to/capture.pcap"})

# Get conversation statistics
client.request("conversation_statistics", {"file": "/path/to/capture.pcap"})

# Get expert information
client.request("expert_info", {"file": "/path/to/capture.pcap"})

Docker Sandbox Support

Run commands in an isolated Docker environment:

# Basic command execution in sandbox
client.request("sandbox_execute", {
    "command": "cat /etc/os-release",
    "memory_limit": "2g",
    "cpu_limit": 1,
    "network_mode": "none",
    "timeout": 30
})

# Execute with file transfer
client.request("sandbox_execute", {
    "command": "python3 script.py",
    "input_files": {
        "local_path": "/path/to/script.py",
        "container_path": "/script.py"
    },
    "output_files": {
        "container_path": "/output.txt",
        "local_path": "/path/to/save/output.txt"
    }
})

Configuration

The MCP server can be configured using a YAML or JSON configuration file:

server:
  host: "0.0.0.0"
  port: 8000
  log_level: "info"

tools:
  nmap:
    path: "/usr/bin/nmap"
    timeout: 300
  objdump:
    path: "/usr/bin/objdump"
  nm:
    path: "/usr/bin/nm"
  strings:
    path: "/usr/bin/strings"
  tshark:
    path: "/usr/bin/tshark"

sandbox:
  enabled: true
  default_image: "ubuntu-systemd:22.04"
  memory_limit: "2g"
  cpu_limit: 1
  network_mode: "none"
  timeout: 60

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.