Wireshark MCP Server
A Model Context Protocol server that enables AI assistants to perform network packet analysis, capture, and security operations on a remote machine via Wireshark/tshark.
README
Wireshark MCP Server
A Model Context Protocol (MCP) server that provides network packet analysis capabilities via Wireshark/tshark on a remote machine (e.g., Kali Linux).
This server enables AI assistants to perform sophisticated network traffic analysis, packet capture, protocol inspection, and security-focused operations through a standardized MCP interface.
Features
- Live Packet Capture - Capture network traffic on remote interfaces with BPF filters
- PCAP Analysis - Read and analyze existing pcap files
- Protocol Statistics - Generate protocol hierarchy, conversations, endpoints, and I/O statistics
- Stream Reconstruction - Follow TCP, UDP, HTTP, and TLS streams
- File Extraction - Extract files from HTTP, SMB, DICOM, IMF, and TFTP traffic
- Deep Packet Inspection - Decode packets with full protocol details
- Credential Extraction - Search for credentials in HTTP Basic Auth, FTP, Telnet, and form submissions
- HTTP Object Export - List and export HTTP objects from captures
Prerequisites
- Node.js 18+
- SSH access to a remote machine with tshark installed (e.g., Kali Linux)
- SSH key-based authentication configured (password-less)
sudoaccess on the remote machine for packet capture
Installation
git clone https://github.com/schwarztim/sec-wireshark-mcp.git
cd sec-wireshark-mcp
npm install
npm run build
Configuration
Set the following environment variables:
| Variable | Description | Default |
|---|---|---|
WIRESHARK_SSH_HOST |
SSH hostname or IP of the remote machine | kali |
WIRESHARK_SSH_USER |
SSH username (optional if using SSH config) | (empty) |
WIRESHARK_PCAP_DIR |
Directory on remote host for pcap files | /tmp/mcp-pcaps |
Example Configuration
export WIRESHARK_SSH_HOST="192.168.1.100"
export WIRESHARK_SSH_USER="kali"
Or use an SSH config entry:
# ~/.ssh/config
Host kali
HostName 192.168.1.100
User kali
IdentityFile ~/.ssh/id_rsa
Usage with Claude Desktop
Add to your Claude Desktop configuration (~/.claude/user-mcps.json or Claude Desktop settings):
{
"mcpServers": {
"wireshark": {
"command": "node",
"args": ["/path/to/sec-wireshark-mcp/dist/index.js"],
"env": {
"WIRESHARK_SSH_HOST": "kali",
"WIRESHARK_SSH_USER": "kali"
}
}
}
}
Available Tools
tshark_list_interfaces
List available network interfaces on the remote machine for packet capture.
tshark_capture
Start packet capture on a specified interface.
Parameters:
interface(required): Network interface (e.g.,eth0,wlan0)count: Number of packets to capture (default: 10, max: 1000)filter: BPF capture filter (e.g.,port 80,host 192.168.1.1)timeout: Capture timeout in seconds (default: 10, max: 60)outputFile: Save capture to pcap file on remote host
tshark_read_pcap
Read and analyze a pcap file.
Parameters:
file(required): Path to the pcap file on remote hostfilter: Wireshark display filtercount: Maximum packets to return (default: 100, max: 1000)fields: Specific fields to extract (e.g.,['ip.src', 'ip.dst', 'tcp.port'])
tshark_filter
Apply a display filter to a pcap file.
Parameters:
file(required): Path to the pcap filefilter(required): Display filter (e.g.,http.request,dns,tcp.flags.syn == 1)outputFormat:json,text, orfields(default:json)fields: Fields to extract when usingfieldsformat
tshark_stats
Generate protocol statistics from a pcap file.
Parameters:
file(required): Path to the pcap filetype(required):hierarchy,conversations,endpoints,io,http, ordnsprotocol: Protocol for conversations/endpoints (e.g.,tcp,udp,ip)
tshark_follow_stream
Reconstruct a TCP, UDP, HTTP, or TLS stream.
Parameters:
file(required): Path to the pcap fileprotocol(required):tcp,udp,http, ortlsstreamIndex: Stream index number (default: 0)format:ascii,hex, orraw(default:ascii)
tshark_extract_files
Extract files from protocol traffic.
Parameters:
file(required): Path to the pcap fileprotocol:http,dicom,imf,smb, ortftp(default:http)outputDir: Directory for extracted files (default:/tmp/mcp-extracted)
tshark_decode
Deep packet inspection with full protocol details.
Parameters:
file(required): Path to the pcap filepacketNumber: Specific packet number to decodefilter: Display filter to select packetsprotocols: Specific protocols to show (e.g.,['http', 'tcp', 'ip'])verbose: Show all protocol details (default: false)
tshark_extract_credentials
Search for potential credentials in network traffic.
Parameters:
file(required): Path to the pcap file
Searches for HTTP Basic Auth, FTP credentials, HTTP POST form data, and Telnet data.
tshark_export_objects
List and export HTTP objects from a capture.
Parameters:
file(required): Path to the pcap filelistOnly: Only list objects without extracting (default: true)outputDir: Directory for extracted objects
Security Considerations
- This server executes commands on a remote machine via SSH
- Input sanitization is implemented to prevent command injection
- Use SSH key authentication with appropriate permissions
- Consider network segmentation for the capture machine
- The remote machine requires
sudoaccess for live capture - Credential extraction features should be used only for authorized security testing
Development
# Run in development mode
npm run dev
# Build for production
npm run build
# Start production server
npm start
License
MIT License - see LICENSE for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Related Projects
- Model Context Protocol - The protocol specification
- Wireshark - Network protocol analyzer
- tshark - Terminal-based Wireshark
推荐服务器
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。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。