unraidlisted

Query and monitor an Unraid NAS/homelab server — array health, disk temperatures, Docker containers, virtual machines, system metrics, notifications, alerts, shares, UPS status, log files, network, plugins, parity history, registration, rclone backups, remote access, and Unraid Connect. Use this skill whenever the user asks about their Unraid server, array state, disk health, SMART status, parity check, Docker containers running on Unraid, Unraid VMs, Unraid memory or CPU usage, Unraid notifications or alerts, Unraid shares, UPS battery on Unraid, Unraid logs, or anything related to an Unraid system. Always invoke this skill when the user mentions "unraid", "array", "parity", "Unraid docker", "Unraid metrics", or asks about NAS health on an Unraid box — even if they don't use the word "skill".
dinglebear-ai/runraid · ★ 3 · AI & Automation · score 71

Install: claude install-skill dinglebear-ai/runraid

# Unraid Server Skill Read-only access to an Unraid NAS server. Three access tiers in priority order: 1. **MCP tool** `unraid` (preferred when available) 2. **CLI binary** `runraid` (fallback) 3. **Direct GraphQL curl** (last resort) All data actions are read-only — nothing modifies the server. --- ## Tier 1 — MCP Tool (preferred) The MCP server exposes a single tool named `unraid` that accepts an `action` parameter. ``` unraid(action="<action>") ``` ### All actions List actions (`disks`, `docker`, `vms`, `shares`, `services`, `plugins`, `parity_history`, `notifications`) accept optional pagination/filtering params on the **MCP surface**: `limit`, `offset`, and where relevant `state` / `name` filters. They return a `{items, total, limit, offset, has_more, next_offset}` envelope. MCP responses are truncated at ~40 KB. (The CLI does not take these params.) | Action | What it returns | Required params | Optional params | |--------|----------------|-----------------|-----------------| | `array` | Array state, capacity (TB), parity status, data disks, cache pools | — | — | | `disks` | All physical disks: SMART status, temp, size, interface, partitions | — | `limit`, `offset`, `name` | | `docker` | All containers: name, state, status, ports, update availability | — | `limit`, `offset`, `state`, `name` | | `docker_logs` | Container log lines | `id` (container ID) | `tail` (default 100) | | `vms` | Virtual machines and their state | — | `limit`, `offset`, `state`, `name` | |