SkillAgentSearch skills...

zeek-mcp

MCP server for Zeek + Suricata network security monitoring logs. Query, hunt, and correlate NSM telemetry from an AI client.

Install / Use

claude mcp add lidless-labs -- npx -y github:lidless-labs/zeek-mcp

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

83/100

Category

Security

Supported Platforms

Claude Code
Claude Desktop

Our assessment of zeek-mcp

zeek-mcp scores 83/100 on our quality scale, 879th of 1,097 Security skills we index.

Its MCP Server is 24 KB long, well organised into 46 sections with 15 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 21 days ago, so zeek-mcp is actively maintained.
  • Our last check on 2026-11-12 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 92/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-13. Automated pattern scan on 2026-11-13. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

zeek-mcp compared with similar skills

All 4 of these similar skills score higher than zeek-mcp; compare them before choosing.

SkillScoreStarsUpdatedFormat
zeek-mcp (this skill)by lidless-labs83321d agoMCP Server
Agent-Reachby Panniantong100113.3k12d agoCLAUDE.md
hyperframesby heygen-com10087.1ktodayCLAUDE.md
rufloby ruvnet10082.1ktodayCLAUDE.md
headroomby headroomlabs-ai10080.2ktodayCLAUDE.md

Frequently asked questions

How do I install zeek-mcp?
Run claude mcp add lidless-labs -- npx -y github:lidless-labs/zeek-mcp. The install tabs above show the steps for each supported agent.
Which AI agents does zeek-mcp work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is zeek-mcp safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 92/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is zeek-mcp still maintained?
The repository was last updated 21 days ago, so zeek-mcp is actively maintained.
<p align="center"> <img src="docs/assets/zeek-mcp-social-preview.jpg" alt="zeek-mcp banner" width="900"> </p> <p align="center"> <a href="https://lidless.dev"><img src="docs/assets/marks/zeek-mcp-circle.png" width="48" alt="Lidless Labs"></a> </p> <h1 align="center">zeek-mcp</h1> <p align="center"><strong>Analyze Zeek and Suricata network logs from your AI client.</strong></p> <p align="center"> <a href="https://lidless.dev/zeek-mcp"><strong>Website</strong></a> &nbsp;&middot;&nbsp; <a href="https://www.npmjs.com/package/zeek-mcp">npm</a> &nbsp;&middot;&nbsp; <a href="#tools">Tools</a> &nbsp;&middot;&nbsp; <a href="#quickstart">Quickstart</a> </p> <p align="center"> <img src="https://shieldcn.dev/github/ci/lidless-labs/zeek-mcp.svg?branch=main&workflow=ci.yml" alt="CI status"> <img src="https://shieldcn.dev/npm/zeek-mcp.svg" alt="npm version"> <img src="https://shieldcn.dev/badge/MCP-server-8A2BE2.svg" alt="Model Context Protocol server"> <img src="https://shieldcn.dev/badge/license-MIT-green.svg" alt="MIT license"> </p>

zeek-mcp is a Model Context Protocol (MCP) server that lets an AI client read, query, and correlate Zeek and Suricata network security monitoring logs. It exists because network telemetry lives in dense per-protocol log files (conn, dns, http, ssl, files, notice, plus Suricata eve.json) that are tedious to grep by hand during an investigation, and an LLM is good at pivoting across them if you give it structured access. It differs from a generic log-reader MCP by speaking Zeek and Suricata natively: it parses both JSON and TSV, understands CIDR and wildcard matching, walks date-rotated and gzipped archives, and ships purpose-built detections (beaconing, DNS tunneling, JA3 hunting, anomaly and baseline analysis) rather than handing the model raw text.

What it does

zeek-mcp turns a Zeek and Suricata sensor into a queryable surface for an AI agent doing network security monitoring (NSM). Point it at your Zeek log directory and Suricata eve.json, register it with any MCP client, and the model can search connection logs, follow a connection UID across every log type, profile DNS for DGA and tunneling, inspect SSL/TLS certificates and JA3 fingerprints, find executable downloads on the wire, cross-reference Suricata alerts against Zeek context, and escalate findings into TheHive or MISP. Detection logic that would otherwise be a pile of ad-hoc queries (C2 beaconing by interval regularity, statistical anomaly detection, network baselining) is exposed as first-class tools, so the agent asks one question instead of reconstructing the analysis from raw logs every time.

It reads logs; it does not run the sensor, mutate capture, or replace your SIEM. Everything is read-only against Zeek and Suricata data, with the single exception of the optional TheHive and MISP tools that create alerts, cases, and events when you provide credentials.

Installation

git clone https://github.com/lidless-labs/zeek-mcp.git
cd zeek-mcp
npm install
npm run build

Prerequisites

  • Node.js 22+
  • Zeek sensor generating logs (JSON or TSV format)
  • Suricata (optional, for IDS alert correlation)

Quickstart

zeek-mcp is published on npm and runs over stdio, so any MCP client can launch it with npx. Add this to your client's MCP config (the example below is for Claude Desktop / Claude Code, adjust env paths to your sensor):

{
  "mcpServers": {
    "zeek": {
      "command": "npx",
      "args": ["-y", "zeek-mcp"],
      "env": {
        "ZEEK_LOG_DIR": "/opt/zeek/logs/current",
        "ZEEK_LOG_FORMAT": "tsv",
        "SURICATA_EVE_LOG": "/opt/suricata/logs/eve.json"
      }
    }
  }
}

Then ask your agent something like "summarize the top talkers in the last connection log and flag any beaconing" and it will call the relevant tools.

To try it locally against the bundled sample data:

npx -y zeek-mcp   # or: git clone, npm install, npm run build, then node dist/index.js

Set ZEEK_LOG_DIR to the included test-data/ directory to explore without a live sensor (see Development).

Usage

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "zeek": {
      "command": "npx",
      "args": ["-y", "zeek-mcp"],
      "env": {
        "ZEEK_LOG_DIR": "/opt/zeek/logs/current",
        "ZEEK_LOG_FORMAT": "tsv",
        "SURICATA_EVE_LOG": "/opt/suricata/logs/eve.json"
      }
    }
  }
}

Claude Code

claude mcp add zeek \
  --env ZEEK_LOG_DIR=/opt/zeek/logs/current \
  --env ZEEK_LOG_FORMAT=tsv \
  --env SURICATA_EVE_LOG=/opt/suricata/logs/eve.json \
  -- npx -y zeek-mcp

Add --scope user to make it available from any directory instead of only the current project.

OpenClaw

With the published package:

openclaw mcp set zeek '{
  "command": "npx",
  "args": ["-y", "zeek-mcp"],
  "env": {
    "ZEEK_LOG_DIR": "/opt/zeek/logs/current",
    "ZEEK_LOG_FORMAT": "tsv",
    "SURICATA_EVE_LOG": "/opt/suricata/logs/eve.json"
  }
}'

Or, when running from a source checkout instead of the npm package, point command/args at the built dist/index.js:

openclaw mcp set zeek '{
  "command": "node",
  "args": ["/absolute/path/to/zeek-mcp/dist/index.js"],
  "env": {
    "ZEEK_LOG_DIR": "/opt/zeek/logs/current",
    "ZEEK_LOG_FORMAT": "tsv",
    "SURICATA_EVE_LOG": "/opt/suricata/logs/eve.json"
  }
}'

Then restart the OpenClaw gateway so the new server is picked up:

systemctl --user restart openclaw-gateway
openclaw mcp list   # confirm "zeek" is registered

Codex CLI

Codex CLI registers MCP servers via codex mcp add:

codex mcp add zeek \
  --env ZEEK_LOG_DIR=/opt/zeek/logs/current \
  --env ZEEK_LOG_FORMAT=tsv \
  --env SURICATA_EVE_LOG=/opt/suricata/logs/eve.json \
  -- npx -y zeek-mcp

Codex writes the entry to ~/.codex/config.toml under [mcp_servers.zeek]. Verify with codex mcp list.

Standalone

ZEEK_LOG_DIR=/opt/zeek/logs/current ZEEK_LOG_FORMAT=tsv node dist/index.js

Development

ZEEK_LOG_DIR=./test-data npm run dev

Tools

zeek-mcp registers 39 tools. Read-only Zeek/Suricata query and analysis tools make up most of the set; TheHive/MISP creation and PCAP replay require the mutation gate described below.

Connection Analysis

| Tool | Description | |------|-------------| | zeek_query_connections | Search connection logs with flexible filters (CIDR, protocol, duration, bytes) | | zeek_connection_summary | Statistical summary: top talkers, services, bytes, connection counts | | zeek_long_connections | Find long-lived connections (potential C2 beacons, tunnels) |

DNS Analysis

| Tool | Description | |------|-------------| | zeek_query_dns | Search DNS queries with domain wildcards and response code filtering | | zeek_dns_summary | Top domains, NXDOMAIN counts (DGA detection), query type distribution | | zeek_dns_tunneling_check | Detect DNS tunneling via entropy analysis and encoding detection |

HTTP Analysis

| Tool | Description | |------|-------------| | zeek_query_http | Search HTTP requests by host, URI, method, user agent, status code | | zeek_suspicious_http | Find suspicious HTTP: POSTs to IPs, unusual agents, large bodies, base64 in URLs |

SSL/TLS Analysis

| Tool | Description | |------|-------------| | zeek_query_ssl | Search SSL/TLS by SNI, version, validation status, certificate fields | | zeek_expired_certs | Find expired, self-signed, or invalid certificates |

File Analysis

| Tool | Description | |------|-------------| | zeek_query_files | Search file extractions by MIME type, hash, filename, size | | zeek_executable_downloads | Find executable transfers (PE, ELF, scripts) on the wire |

Security Notices

| Tool | Description | |------|-------------| | zeek_query_notices | Search Zeek security notices (port scans, invalid certs, custom alerts) |

SSH Analysis

| Tool | Description | |------|-------------| | zeek_query_ssh | Search SSH connections by auth status, direction, client/server | | zeek_ssh_bruteforce | Detect SSH brute force attempts exceeding a failure threshold |

DHCP & Asset Discovery

| Tool | Description | |------|-------------| | zeek_query_dhcp | Search DHCP logs for lease assignments and device discovery | | zeek_dhcp_asset_map | Build MAC-to-IP/hostname asset map for network inventory |

Cross-Log Investigation

| Tool | Description | |------|-------------| | zeek_investigate_host | Full host investigation across all log types | | zeek_investigate_uid | Follow a connection UID across all log types |

Software Discovery

| Tool | Description | |------|-------------| | zeek_software_inventory | List detected software and versions on the network |

Analytics

| Tool | Description | |------|-------------| | zeek_detect_beaconing | Detect C2 beaconing by analyzing connection interval regularity and jitter | | zeek_detect_anomalies | Statistical anomaly detection: port scans, data exfiltration, unusual ports | | zeek_ja3_fingerprints | Extract and analyze JA3/JA3S TLS fingerprints from SSL logs | | zeek_ja3_hunt | Hunt known-malicious JA3 fingerprints (CobaltStrike, Emotet, TrickBot, etc.) across SSL logs | | zeek_network_baseline | Generate a statistical baseline of normal network activity as a reference point | | zeek_detect_outliers | Compare current activity against a baseline and flag statistical outliers |

Suricata IDS

| Tool | Description | |------|-------------| | suricata_query_alerts | Search Suricata alerts by signature, severity, IP, protocol, time | | suricata_alert_summary | High-level alert summary: top signatures, categories, IPs, severity distribution | | suricata_correlate_zeek | Cross-reference Suricata alerts with Zeek logs for full context | | suricata_eve_stats | Suricata engine statistics: packets, flows, detection performance |

PCAP Analysis

| Tool | Description | |------|-------------| | pcap_list | List available PCAP files in the capture directory with sizes and timestamps | | pcap_analyze | Replay a PCAP file through Zeek and return the generated log summary. Requires mutation gate. |

Incident Response

| Tool | Description | |------|-------------| | thehive_create_alert | Create a TheHive alert from NIDS findings (observables, severity, TLP). Requires mutation gate. | | thehive_create_case | Create a TheHive case for in-depth, collaborative investigation. Requires mutation gate. | | thehive_search_cases | Search existing TheHive cases and alerts for related work or duplicates | | misp_search_iocs | Search MISP for IOCs (IPs, domains, hashes, URLs) and return matching events | | misp_bulk_lookup | Check multiple IOCs against MISP in a single call | | misp_add_event | Create a MISP event from NIDS findings to share threat intelligence. Requires mutation gate. |

Sensor Management

| Tool | Description | |------|-------------| | nids_sensor_status | Live sensor status: log inventory, sizes, freshness, health checks |

External telemetry

Tool descriptions and results identify network, log, filename, and remote service content as untrusted evidence. Returned strings and keys must never be treated as instructions or permission to act. JSON result fields retain their shape, with delimiter characters escaped in the serialized text. String values longer than 4096 characters are shortened and marked with [truncated]. A separate text block carries the provenance notice, so the first result block remains parseable JSON.

PCAP replay still requires ZEEK_ALLOW_MUTATION=1 and `confirm: true

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3
CategorySecurity
Updated21d ago
Forks0

Languages

TypeScript

Trust signals

92/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low
zeek-mcp — MCP Server: Install & Safety Check | SkillAgent