Sponsored by Deepsite.site

Wireshark MCP Server

Created By
A-G-U-P-T-A10 months ago
TShark/Wireshark MCP server for network packet analysis via Claude
Content

Wireshark MCP Server

This project exposes PyShark functionality through the Model Context Protocol (MCP), allowing AI assistants like Claude to interact with network packet capture and analysis capabilities.

Installation

  1. Install the required dependencies:
# Install with uv (recommended)
uv add mcp[cli] pyshark

# Or with pip
pip install mcp[cli] pyshark
  1. Clone this repository:
git clone https://github.com/A-G-U-P-T-A/wireshark-mcp
cd wireshark-mcp

Requirements

  • Python 3.8+
  • TShark (Wireshark's command-line component) must be installed
  • Administrative/root privileges for live packet capture

Usage

Running the server

You can run the server in development mode with the MCP Inspector:

mcp dev pyshark_mcp.py

Or install it directly in Claude Desktop:

mcp install pyshark_mcp.py

Available functionality

This MCP server exposes the following:

Resources

  • pyshark://version - Gets the PyShark version information
  • pyshark://config - Gets the PyShark configuration
  • pyshark://capture-history - Gets history of previous packet captures

Tools

  • list_interfaces - Lists all available network interfaces
  • capture_live_packets - Captures live packets from a network interface
  • read_pcap_file - Reads and analyzes a packet capture file
  • analyze_traffic - Analyzes network traffic patterns from a capture

Advanced tools provided in advanced_captures.py:

  • capture_targeted_traffic - Captures traffic targeted to specific host, port, or protocol
  • capture_to_file - Captures network traffic and saves to a pcap file
  • analyze_http_traffic - Analyzes HTTP traffic from a capture file
  • detect_network_protocols - Detects and reports network protocols in use

Prompts

  • packet_capture_help - Provides help information about packet capturing with PyShark

Example usage in Claude

Once the server is installed in Claude Desktop, you can interact with it like this:

You: What interfaces are available for network capture?

Claude: Let me check the available network interfaces on your system.
[Calls list_interfaces tool]

You: Can you capture HTTP traffic for 10 seconds?

Claude: I'll capture HTTP traffic for 10 seconds.
[Calls capture_live_packets with appropriate parameters]

You: Can you analyze the traffic I just captured?

Claude: Here's an analysis of the captured traffic:
[Calls analyze_traffic to provide insights]

Remember to always ensure you have permission to capture network traffic.

Security Considerations

Network packet capture is a sensitive operation. Please ensure:

  1. You have proper authorization to capture network traffic
  2. You comply with all applicable laws and regulations
  3. You don't capture sensitive or private data inadvertently
  4. You handle capture files securely to prevent unauthorized access

Requirements

  • PyShark: Python wrapper for TShark
  • TShark: Command-line version of Wireshark (must be installed separately)
  • Administrative privileges: Often required for live packet capture

Customization

You can customize this MCP server by:

  1. Adding more advanced capture and analysis tools
  2. Implementing filters for specific traffic types
  3. Creating specialized analysis functions for protocols of interest
  4. Extending the capture history management capabilities
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Tavily Mcp
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
WindsurfThe new purpose-built IDE to harness magic
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
ChatWiseThe second fastest AI chatbot™
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Playwright McpPlaywright MCP server
CursorThe AI Code Editor
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
DeepChatYour AI Partner on Desktop
Serper MCP ServerA Serper MCP Server
Amap Maps高德地图官方 MCP Server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。