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.
{
"mcpServers": {
"wireshark-mcp": {
"command": "uvx",
"args": [
"wireshark-mcp"
]
}
}
}{
"mcpServers": {
"wireshark-mcp": {
"command": "uvx",
"args": [
"wireshark-mcp"
]
}
}
}{
"mcpServers": {
"wireshark-mcp": {
"command": "uvx",
"args": [
"wireshark-mcp"
]
}
}
}{
"servers": {
"wireshark-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"wireshark-mcp"
]
}
}
}claude mcp add wireshark-mcp -- uvx wireshark-mcpTools & capabilities
Tools this server exposes to the agent.
wireshark_open_file— Open and initialize a .pcap file for analysiswireshark_security_audit— Run a comprehensive security audit on the capturewireshark_quick_analysis— Perform a quick overview analysis of the capturewireshark_extract_dns_queries— Extract and analyze DNS queries from the capturewireshark_extract_http_requests— Extract HTTP requests and responseswireshark_extract_tls_handshakes— Extract TLS/SSL handshake datawireshark_check_threats— Check for known threats and suspicious indicatorswireshark_credential_scan— Scan for exposed credentials in trafficwireshark_port_scan_detection— Detect port scanning activitywireshark_dns_tunnel_detection— Detect DNS tunneling attemptswireshark_dos_detection— Detect denial-of-service patternswireshark_protocol_hierarchy— Generate protocol hierarchy statisticswireshark_endpoints— List and analyze network endpointswireshark_conversations— Analyze conversations between hostswireshark_io_graph— Generate I/O graph statisticswireshark_expert_info— Extract expert analysis and warningswireshark_tcp_health— Analyze TCP connection healthwireshark_arp_spoofing_detection— Detect ARP spoofing attemptswireshark_packet_list— Retrieve packet list from capturewireshark_packet_details— Get 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
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.
Yes, it's MIT licensed and open source. It requires Wireshark (also free) and Python 3.10+ to be installed on your system.
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.
Python 3.10+ and Wireshark with tshark on your PATH. Optional tools (capinfos, mergecap, editcap, dumpcap, text2pcap) are auto-detected to enable extra features.
Yes, it includes dedicated security tools for threat detection, credential scanning, port scan detection, DNS tunnel detection, DoS detection, and ARP spoofing detection.
No, it runs locally on your machine. It only requires Wireshark and tshark to be installed.
README (reference)
Source of truth, from the repository.
Give your AI assistant a packet analyzer.
Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.
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:
| Category | Highlights | Count |
|---|---|---|
| Agentic Workflows | wireshark_security_audit, wireshark_quick_analysis, wireshark_open_file | 4 |
| Packet Analysis | Packet list, details, bytes, context, stream follow, search | 7 |
| Data Extraction | HTTP requests, DNS queries, TLS handshakes, field extraction | 6 |
| Statistics | Protocol hierarchy, endpoints, conversations, I/O graph, expert info | 6 |
| Security | Threat intel, credential scan, port scan, DNS tunnel, DoS detection | 6 |
| Protocol Deep Dive | TCP health, ARP spoofing, SMTP, DHCP | 5 |
| File Ops & Capture | Live capture, merge, filter-save, file info | 5 |
| Suite Utilities | editcap trim/split/dedup, text2pcap import | 5 |
| Decode & Visualize | Payload decode, traffic plot, protocol tree | 3 |
The server starts with only tshark required. Optional tools (capinfos, mergecap, editcap, dumpcap, text2pcap) are auto-detected and enable extra features when present.
Documentation
| Topic | Link |
|---|---|
| Platform setup (macOS/Linux/Windows) | docs/platform-validation.md |
| Manual client configuration | docs/manual-configuration.md |
| Prompt templates | docs/prompt-engineering.md |
| Release checklist | docs/release-checklist.md |
| Contributing | CONTRIBUTING.md |
| Changelog | CHANGELOG.md |
| Security policy | SECURITY.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
Scrapling MCP Server
Give your AI agent stealth web scraping with Cloudflare bypass and CSS selection, powered by Scrapling.
Chrome DevTools MCP
Give your AI coding agent full control of a live Chrome browser for automation, debugging, and performance analysis.
com.puter/mcp-server
Let AI agents manage your Puter files, websites, and serverless workers over MCP.
Browser automation for AI agents via MCP, powering ByteDance's Agent TARS hybrid GUI/DOM browser control.
Run arbitrary shell commands from an MCP-connected AI agent.
Filesystem access MCP server from ByteDance's UI-TARS/Agent TARS ecosystem.