WireMCP MCP server

WireMCP is a Model Context Protocol (MCP) server that enhances Large Language Models with network traffic analysis capabilities. It captures and processes live network data through Wireshark's tshark, enabling LLMs to assist with threat hunting, network diagnostics, and anomaly detection by providing structured context from network traffic.

Prerequisites

• Mac, Windows, or Linux operating system
• Wireshark with tshark installed and accessible in PATH
• Node.js (v16+ recommended)
• npm (for dependency installation)

Installation

1. Clone the repository:

   git clone https://github.com/0xkoda/WireMCP.git
   cd WireMCP
   

2. Install dependencies:

   npm install
   

3. Run the MCP server:

   node index.js
   

Note: WireMCP will automatically detect tshark in your PATH or fall back to common install locations such as /Applications/Wireshark.app/Contents/MacOS/tshark on macOS.

Setting Up with MCP Clients

Cursor Setup

Edit mcp.json in Cursor's settings:

{
  "mcpServers": {
    "wiremcp": {
      "command": "node",
      "args": [
        "/ABSOLUTE_PATH_TO/WireMCP/index.js"
      ]
    }
  }
}

The configuration file is typically located at /Users/YOUR_USER/Library/Application Support/Claude/claude_desktop_config.json on macOS.

Other MCP Clients

WireMCP works with any MCP-compliant client. Simply configure the client to use the command node /path/to/WireMCP/index.js in their MCP server settings.

Available Tools

WireMCP provides several tools for network analysis:

• capture_packets: Captures live traffic and returns packet data as JSON
• get_summary_stats: Provides protocol hierarchy statistics
• get_conversations: Shows TCP/UDP conversation statistics
• check_threats: Captures IPs and checks them against the URLhaus blacklist
• check_ip_threats: Performs targeted threat intelligence lookups for specific IP addresses
• analyze_pcap: Analyzes saved PCAP files to provide packet data in JSON format
• extract_credentials: Scans PCAP files for potential credentials from various protocols

Example Usage

Checking for Threats

When running the check_threats tool, you might see output like:

Captured IPs:
174.67.0.227
52.196.136.253

Threat check against URLhaus blacklist:
No threats detected in URLhaus blacklist.

Analyzing a PCAP File

Using analyze_pcap on a capture file produces structured JSON output:

{
  "content": [{
    "type": "text",
    "text": "Analyzed PCAP: ./capture.pcap\n\nUnique IPs:\n192.168.0.2\n192.168.0.1\n\nProtocols:\neth:ethertype:ip:tcp\neth:ethertype:ip:tcp:telnet\n\nPacket Data:\n[{\"layers\":{\"frame.number\":[\"1\"],\"ip.src\":[\"192.168.0.2\"],\"ip.dst\":[\"192.168.0.1\"],\"tcp.srcport\":[\"1550\"],\"tcp.dstport\":[\"23\"]}}]"
  }]
}

LLMs can interpret these outputs to provide:

• Natural language explanations of network activity
• Identification of patterns and security concerns
• Context-aware recommendations
• Human-readable reports of network traffic

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.