WireMCP — это сервер протокола Model Context Protocol (MCP), разработанный для предоставления Large Language Models (LLM) возможностей анализа сетевого трафика в реальном времени. Используя инструменты, построенные на базе tshark Wireshark, WireMCP захватывает и обрабатывает живые сетевые данные, предоставляя LLM структурированный контекст для помощи в таких задачах, как охота на угрозы, диагностика сети и обнаружение аномалий.

Особенности

WireMCP предоставляет клиентам MCP следующие инструменты, улучшая понимание сетевой активности в LLM:

• capture_packets: Захватывает живой трафик и возвращает сырые пакетные данные в формате JSON, позволяя LLM анализировать детали на уровне пакетов (например, IP-адреса, порты, HTTP-методы).
• get_summary_stats: Предоставляет статистику иерархии протоколов, предоставляя LLM обзор состава трафика (например, использование TCP против UDP).
• get_conversations: Предоставляет статистику разговоров TCP/UDP, позволяя LLM отслеживать потоки коммуникации между конечными точками.
• check_threats: Захватывает IP и проверяет их по черному списку URLhaus, оснащая LLM контекстом разведки угроз для выявления вредоносной активности.

WireMCP

WireMCP is a Model Context Protocol (MCP) server designed to empower Large Language Models (LLMs) with real-time network traffic analysis capabilities. By leveraging tools built on top of Wireshark’s tshark, WireMCP captures and processes live network data, providing LLMs with structured context to assist in tasks like threat hunting, network diagnostics, and anomaly detection.

Features

WireMCP exposes the following tools to MCP clients, enhancing LLM understanding of network activity:

• capture_packets: Captures live traffic and returns raw packet data as JSON, enabling LLMs to analyze packet-level details (e.g., IP addresses, ports, HTTP methods).
• get_summary_stats: Provides protocol hierarchy statistics, giving LLMs an overview of traffic composition (e.g., TCP vs. UDP usage).
• get_conversations: Delivers TCP/UDP conversation statistics, allowing LLMs to track communication flows between endpoints.
• check_threats: Captures IPs and checks them against the URLhaus blacklist, equipping LLMs with threat intelligence context for identifying malicious activity.
• check_ip_threats: Performs targeted threat intelligence lookups for specific IP addresses against multiple threat feeds, providing detailed reputation and threat data.
• analyze_pcap: Analyzes PCAP files to provide comprehensive packet data in JSON format, enabling detailed post-capture analysis of network traffic.
• extract_credentials: Scans PCAP files for potential credentials from various protocols (HTTP Basic Auth, FTP, Telnet), aiding in security audits and forensic analysis.

How It Helps LLMs

WireMCP bridges the gap between raw network data and LLM comprehension by:

• Contextualizing Traffic: Converts live packet captures into structured outputs (JSON, stats) that LLMs can parse and reason about.
• Threat Detection: Integrates IOCs (currently URLhaus) to flag suspicious IPs, enhancing LLM-driven security analysis.
• Diagnostics: Offers detailed traffic insights, enabling LLMs to assist with troubleshooting or identifying anomalies.
• Narrative Generation: LLM’s can Transform complex packet captures into coherent stories, making network analysis accessible to non-technical users.

Installation

Prerequisites

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

Setup

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: Ensure tshark is in your PATH. WireMCP will auto-detect it or fall back to common install locations (e.g., /Applications/Wireshark.app/Contents/MacOS/tshark on macOS).

Usage with MCP Clients