arkime-mcp-server
An MCP server for Arkime full packet capture that enables AI assistants to search network sessions, investigate traffic patterns, and monitor capture health through various network analysis tools.
README
arkime-mcp-server
An MCP server for Arkime full packet capture. Lets AI assistants search network sessions, investigate traffic patterns, and monitor capture health.
Tools
| Tool | Description |
|---|---|
search_sessions |
Search sessions with Arkime expressions, returns source/dest IPs, ports, protocols, bytes, geo, and AS info |
get_session_detail |
Full decoded protocol detail for a single session |
get_session_packets |
Decoded packet data for a session |
top_talkers |
Top N values for any field by session count (hosts, ports, domains, etc.) |
connections_graph |
Network connection graph — nodes and links with byte/packet/session counts |
unique_destinations |
Distinct external IPs contacted by an internal host |
dns_lookups |
DNS queries captured in traffic, filterable by domain pattern or source IP |
reverse_dns |
PTR/reverse DNS lookup for an IP |
external_connections |
Sessions going to non-RFC1918 destinations, sorted by bytes |
geo_summary |
Destination traffic breakdown by country |
capture_status |
Arkime cluster health — node count, shard status, OpenSearch version |
pcap_files |
PCAP capture files with sizes, packet counts, and time ranges |
list_fields |
Available Arkime session fields for use in search expressions |
Setup
npm install
npm run build
Configuration
Set environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
ARKIME_URL |
No | http://192.168.5.176:8005 |
Arkime viewer URL |
ARKIME_USER |
No | mcp |
Arkime API username |
ARKIME_PASSWORD |
Yes | — | Arkime API password |
Usage with Claude Code
Add to your MCP settings (e.g., .mcp.json):
{
"mcpServers": {
"arkime": {
"command": "node",
"args": ["/path/to/arkime-mcp-server/build/index.js"],
"env": {
"ARKIME_PASSWORD": "your-password"
}
}
}
}
Authentication
Arkime uses HTTP Digest authentication. The server handles this via the digest-fetch library.
License
MIT
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.