
mcpcap
Enables LLMs to analyze network packet captures (PCAP files) from local or remote sources through a modular architecture. Supports DNS traffic analysis with structured JSON responses for network security and troubleshooting tasks.
README
mcpcap
A modular Python MCP (Model Context Protocol) Server for analyzing PCAP files. mcpcap enables LLMs to read and analyze network packet captures from local or remote sources, providing structured JSON responses about network traffic.
Overview
mcpcap uses a modular architecture to analyze different network protocols found in PCAP files. Each module focuses on a specific protocol, allowing for targeted analysis and easy extensibility. The server leverages the powerful scapy library for packet parsing and analysis.
Key Features
- Modular Architecture: Easily extensible to support new protocols
- Local & Remote PCAP Support: Read files from local directories or HTTP servers
- Scapy Integration: Leverages scapy's comprehensive packet parsing capabilities
- MCP Server: Integrates seamlessly with LLM clients via Model Context Protocol
- JSON Responses: Structured data format for easy LLM consumption
Installation
mcpcap requires Python 3.10 or greater.
Using pip
pip install mcpcap
Using uv
uv add mcpcap
Using uvx (for one-time usage)
uvx mcpcap
Quick Start
-
Start the MCP Server:
mcpcap --pcap-path /path/to/pcap/files
-
Connect your LLM client to the MCP server
-
Ask questions about your network traffic:
- "What domain was queried the most in the DNS traffic?"
- "Show me all DNS queries for example.com"
- "What are the top 5 queried domains?"
Modules
DNS Module
The DNS module analyzes Domain Name System packets in PCAP files.
Capabilities:
- Extract DNS queries and responses
- Identify queried domains and subdomains
- Analyze query types (A, AAAA, MX, etc.)
- Track query frequency and patterns
- Identify DNS servers used
Example Usage:
# LLM can ask: "What domains were queried in this PCAP?"
# mcpcap will return structured JSON with DNS query information
Configuration
PCAP Sources
Local Directory:
mcpcap --pcap-path /local/path/to/pcaps
Remote HTTP Server:
mcpcap --pcap-url http://example.com/pcaps/
Module Selection
mcpcap --modules dns --pcap-path /path/to/files
Example
An example PCAP file (example.pcap
) containing DNS traffic is included with the project to help you get started.
Architecture
mcpcap's modular design makes it easy to extend support for new protocols:
- Core Engine: Handles PCAP file loading and basic packet processing
- Protocol Modules: Individual modules for specific protocols (DNS, etc.)
- MCP Interface: Translates between LLM queries and packet analysis results
- Output Formatter: Converts analysis results to structured JSON
Adding New Modules
New protocol modules can be added by:
- Implementing the module interface
- Defining scapy display filters for the protocol
- Creating analysis functions specific to the protocol
- Registering the module with the core engine
Future modules might include:
- BGP (Border Gateway Protocol)
- HTTP/HTTPS traffic analysis
- TCP connection tracking
- And more!
Remote Access
mcpcap supports reading PCAP files from remote HTTP servers without authentication. Future versions may include support for Basic Authentication and other security mechanisms.
Contributing
Contributions are welcome! Whether you want to:
- Add support for new protocols
- Improve existing modules
- Enhance the MCP interface
- Add new features
Please feel free to open issues and submit pull requests.
License
MIT
Requirements
- Python 3.10+
- scapy
- MCP server dependencies (automatically installed)
Support
For questions, issues, or feature requests, please open an issue on GitHub.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.