PluginBench
MCP Server
Maintained
MIT

io.github.bx33661/wireshark-mcp MCP Server

io.github.bx33661/wireshark-mcp

AI-powered packet analysis with tshark—security audits, threat detection, and network deep-dives in plain English.

What is the io.github.bx33661/wireshark-mcp MCP server?

The Wireshark MCP server wraps tshark and optional Wireshark suite tools into a structured analysis interface for AI assistants. It enables natural-language network packet analysis, threat detection, and security audits on .pcap files through 40+ specialized tools.

This server gives Claude, Cursor, and other MCP clients the ability to analyze network traffic using tshark. Drop a .pcap file and ask questions in plain English—the server extracts DNS queries, HTTP requests, TLS handshakes, detects threats, performs security audits, and generates detailed reports. Ideal for security professionals, network engineers, and incident responders who want AI-assisted packet analysis.

How to install io.github.bx33661/wireshark-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "wireshark-mcp": {
      "command": "uvx",
      "args": [
        "wireshark-mcp"
      ]
    }
  }
}
Cursor
~/.cursor/mcp.json
{
  "mcpServers": {
    "wireshark-mcp": {
      "command": "uvx",
      "args": [
        "wireshark-mcp"
      ]
    }
  }
}
Windsurf
~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "wireshark-mcp": {
      "command": "uvx",
      "args": [
        "wireshark-mcp"
      ]
    }
  }
}
VS Code
.vscode/mcp.json
{
  "servers": {
    "wireshark-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "wireshark-mcp"
      ]
    }
  }
}
Claude Code
claude mcp add wireshark-mcp -- uvx wireshark-mcp

Tools & capabilities

Tools this server exposes to the agent.

  • wireshark_open_fileOpen and initialize a .pcap file for analysis
  • wireshark_security_auditRun a comprehensive security audit on the capture
  • wireshark_quick_analysisPerform a quick overview analysis of the capture
  • wireshark_extract_dns_queriesExtract and analyze DNS queries from the capture
  • wireshark_extract_http_requestsExtract HTTP requests and responses
  • wireshark_extract_tls_handshakesExtract TLS/SSL handshake data
  • wireshark_check_threatsCheck for known threats and suspicious indicators
  • wireshark_credential_scanScan for exposed credentials in traffic
  • wireshark_port_scan_detectionDetect port scanning activity
  • wireshark_dns_tunnel_detectionDetect DNS tunneling attempts
  • wireshark_dos_detectionDetect denial-of-service patterns
  • wireshark_protocol_hierarchyGenerate protocol hierarchy statistics
  • wireshark_endpointsList and analyze network endpoints
  • wireshark_conversationsAnalyze conversations between hosts
  • wireshark_io_graphGenerate I/O graph statistics
  • wireshark_expert_infoExtract expert analysis and warnings
  • wireshark_tcp_healthAnalyze TCP connection health
  • wireshark_arp_spoofing_detectionDetect ARP spoofing attempts
  • wireshark_packet_listRetrieve packet list from capture
  • wireshark_packet_detailsGet detailed information about a specific packet

Use cases

  • Perform security audits on network captures to identify threats, exposed credentials, and suspicious activity
  • Extract and analyze DNS queries, HTTP requests, and TLS handshakes for investigation
  • Detect port scans, DoS attacks, DNS tunneling, and ARP spoofing in network traffic
  • Generate detailed statistics and protocol analysis reports from .pcap files
  • Investigate live network traffic or merge and filter multiple capture files for deeper analysis

io.github.bx33661/wireshark-mcp MCP server FAQ

What is the Wireshark MCP server?

It's an MCP server that wraps tshark (and optional Wireshark tools) into a structured interface. You can ask your AI assistant to analyze .pcap files in plain English, and it will extract data, detect threats, and generate reports using 40+ specialized tools.

Is it free?

Yes, it's MIT licensed and open source. It requires Wireshark (also free) and Python 3.10+ to be installed on your system.

How do I install it in Cursor or Claude?

Run `pip install wireshark-mcp` then `wireshark-mcp install` to auto-configure all detected MCP clients. Restart your AI client and you're done. See docs/manual-configuration.md for manual setup.

What are the prerequisites?

Python 3.10+ and Wireshark with tshark on your PATH. Optional tools (capinfos, mergecap, editcap, dumpcap, text2pcap) are auto-detected to enable extra features.

Can I use it for security audits?

Yes, it includes dedicated security tools for threat detection, credential scanning, port scan detection, DNS tunnel detection, DoS detection, and ARP spoofing detection.

Does it require authentication?

No, it runs locally on your machine. It only requires Wireshark and tshark to be installed.

README (reference)

Source of truth, from the repository.

<div align="center"> <!-- mcp-name: io.github.bx33661/wireshark-mcp --> <img src="Logo.png" width="150" alt="Wireshark MCP" style="margin-top: 20px; margin-bottom: 20px;"> <h1>Wireshark MCP</h1>

Give your AI assistant a packet analyzer.

Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.

<p style="margin-top: 15px;"> <a href="https://github.com/bx33661/Wireshark-MCP/actions/workflows/ci.yml"> <img src="https://img.shields.io/github/actions/workflow/status/bx33661/Wireshark-MCP/ci.yml?style=flat-square&logo=github&label=CI" alt="CI"> </a> <a href="https://github.com/bx33661/Wireshark-MCP/releases/latest"> <img src="https://img.shields.io/github/v/release/bx33661/Wireshark-MCP?style=flat-square&logo=github&color=24292f" alt="GitHub Release"> </a> <a href="https://pypi.org/project/wireshark-mcp/"> <img src="https://img.shields.io/pypi/v/wireshark-mcp?style=flat-square&logo=pypi&color=0066cc" alt="PyPI"> </a> <a href="https://pypi.org/project/wireshark-mcp/"> <img src="https://img.shields.io/pypi/pyversions/wireshark-mcp?style=flat-square&logo=python" alt="Python"> </a> <a href="LICENSE"> <img src="https://img.shields.io/badge/License-MIT-green.svg?style=flat-square" alt="MIT License"> </a> </p> <p> <a href="README.md"><b>English</b></a> • <a href="README_zh.md"><b>中文</b></a> • <a href="CHANGELOG.md"><b>Changelog</b></a> • <a href="CONTRIBUTING.md"><b>Contributing</b></a> </p> </div>

What is this?

An MCP server that wraps tshark (and optional Wireshark suite tools) into a structured analysis interface. Works with Claude Desktop, Claude Code, Cursor, VS Code, and 18+ other MCP clients.

You:    "Find all DNS queries going to suspicious domains in this capture."
Claude: [calls wireshark_extract_dns_queries → wireshark_check_threats]
        "Found 3 queries to domains flagged by URLhaus: ..."

Install

Prerequisites: Python 3.10+ and Wireshark with tshark on PATH.

pip install wireshark-mcp
wireshark-mcp install   # auto-configures all detected MCP clients

Restart your AI client — done.

Run wireshark-mcp doctor if anything looks off. See docs/manual-configuration.md for manual setup or platform-specific notes.


Quick Start

Point your AI client at a .pcap file and try:

Analyze capture.pcap using the Wireshark MCP tools.
Start with wireshark_open_file, then run wireshark_security_audit.
Write findings to report.md.

Tools

40+ tools organized into categories:

CategoryHighlightsCount
Agentic Workflowswireshark_security_audit, wireshark_quick_analysis, wireshark_open_file4
Packet AnalysisPacket list, details, bytes, context, stream follow, search7
Data ExtractionHTTP requests, DNS queries, TLS handshakes, field extraction6
StatisticsProtocol hierarchy, endpoints, conversations, I/O graph, expert info6
SecurityThreat intel, credential scan, port scan, DNS tunnel, DoS detection6
Protocol Deep DiveTCP health, ARP spoofing, SMTP, DHCP5
File Ops & CaptureLive capture, merge, filter-save, file info5
Suite Utilitieseditcap trim/split/dedup, text2pcap import5
Decode & VisualizePayload decode, traffic plot, protocol tree3

The server starts with only tshark required. Optional tools (capinfos, mergecap, editcap, dumpcap, text2pcap) are auto-detected and enable extra features when present.


Documentation

TopicLink
Platform setup (macOS/Linux/Windows)docs/platform-validation.md
Manual client configurationdocs/manual-configuration.md
Prompt templatesdocs/prompt-engineering.md
Release checklistdocs/release-checklist.md
ContributingCONTRIBUTING.md
ChangelogCHANGELOG.md
Security policySECURITY.md

Development

pip install -e ".[dev]"
pytest tests/ -v
ruff check src/ tests/

See CONTRIBUTING.md for the full guide.


<div align="center"> <sub><a href="LICENSE">MIT License</a> · <a href="https://github.com/bx33661/Wireshark-MCP/issues">Report a Bug</a></sub> </div>

Related MCP servers

Give your AI agent stealth web scraping with Cloudflare bypass and CSS selection, powered by Scrapling.

67k
Python
BSD-3-Clause
View repository →

Give your AI coding agent full control of a live Chrome browser for automation, debugging, and performance analysis.

45k
TypeScript
Apache-2.0
View repository →

Let AI agents manage your Puter files, websites, and serverless workers over MCP.

43k
TypeScript
AGPL-3.0
View repository →

Browser automation for AI agents via MCP, powering ByteDance's Agent TARS hybrid GUI/DOM browser control.

37k
TypeScript
Apache-2.0
View repository →

Run arbitrary shell commands from an MCP-connected AI agent.

37k
TypeScript
Apache-2.0
View repository →

Filesystem access MCP server from ByteDance's UI-TARS/Agent TARS ecosystem.

37k
TypeScript
Apache-2.0
View repository →