MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for TheHive: AI-driven incident response, case management, alerts, observables, and Cortex analyzers (SOAR).
npm MIT ★ 1 -
MCP server for Suricata IDS/IPS and Zeek NSM: analyze EVE JSON alerts, hunt threats, and manage rules from an AI client
npm MIT ★ 4 -
MCP server for Zeek + Suricata network security monitoring logs. Query, hunt, and correlate NSM telemetry from an AI client.
npm MIT ★ 3 -
Your photo library outgrew the click-grid. immichctrl gives shells, cron, and agents one typed control surface for Immich, with writes off by default.
npm MIT ★ 6 -
n8n automations are locked behind its own UI. n8nctrl hands workflow inspect, validate, run, and ops to shells, cron, and agents over CLI plus MCP.
npm MIT ★ 1 -
A hallucinated call can mute a real alert. librenmsctrl gives shells, cron, and agents one stdio control surface for LibreNMS devices, ports, and alerts, writes gated.
npm MIT ★ 1 -
One bad call can take down your DNS filtering. adguardctrl gates every AdGuard Home write behind confirm and destructive flags. CLI plus MCP adapter, no daemon.
npm MIT ★ 2 -
Analysts click through a dozen Cortex jobs by hand. cortex-mcp detonates the indicator and hands your agent one aggregated verdict. Destructive actions stay confirm-gated.
npm MIT ★ 1 -
MISP threat intel lives in tabs you never finish reading. misp-mcp turns events, attributes, and IOC lookups into answers your AI client pulls on demand.
npm MIT ★ 2 -
Your SIEM answers live behind a console you babysit. wazuh-mcp reads Wazuh alerts, agents, and CVEs straight into your AI client. Read-only, nothing leaves the box.
npm MIT ★ 9 -
MCP server for the MITRE ATT&CK knowledge base: map alerts to techniques, profile threat groups, analyze detection coverage, and enrich SOC workflows from an AI client.
npm MIT ★ 4 -
Point an agent at your homelab and it can nuke a VM. proxmox-mcp gates every write before the Proxmox API sees it, so an AI client can operate the cluster without owning it.
npm MIT ★ 11