By jmagar
Manage an Unraid NAS server from Claude: monitor system health, array and disk status, Docker containers and VMs, read logs and notifications, and configure server credentials — all through natural language
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
Admin access level
Server config contains admin-level keywords
Requires secrets
Needs API keys or credentials to function
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub jmagar/claude-homelab --plugin unraid-mcpBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
unraid_api_keyAPI key for your Unraid server. Found in Settings → Management Access → API Keys.
${user_config.unraid_api_key}unraid_api_urlYour Unraid server's GraphQL endpoint, e.g. https://tower.local/graphql. No trailing slash.
${user_config.unraid_api_url}GraphQL-backed MCP server for Unraid. Exposes a unified unraid tool for system inspection, management operations, live telemetry, and destructive actions gated by explicit confirmation.
The server translates MCP tool calls into Unraid GraphQL queries and mutations over HTTP and WebSocket. All operations share a single unraid tool routed by action + subaction. Live telemetry uses WebSocket subscriptions that stream real-time data from the Unraid API.
unraid_mcp/ — server, GraphQL client, WebSocket subscriptions, config, and tool handlersskills/unraid/ — client-facing skill docsdocs/ — authentication, destructive-action, and publishing references.claude-plugin/, .codex-plugin/, gemini-extension.json — client manifestsdocker-compose.yaml, Dockerfile, entrypoint.sh — container deploymenttests/ — unit, safety, schema, HTTP-layer, and live coverage| Tool | Purpose |
|---|---|
unraid | Unified action/subaction router for all operations |
unraid_help | Returns this reference as Markdown |
diagnose_subscriptions | Full diagnostic dump of the WebSocket subscription system |
test_subscription_query | Probe a raw GraphQL subscription for schema/debug work |
unraid — action groupsAll operations go through one tool. Pick an action, then a subaction within it.
system — 18 subactionsServer information, metrics, network, and UPS.
| Subaction | Description | Required params |
|---|---|---|
overview | OS, CPU, memory layout, versions, machine ID | — |
array | Array state, capacity, disk health summary | — |
network | Access URLs, HTTP/HTTPS ports, LAN/WAN IPs | — |
registration | License type, key file, expiration | — |
variables | Full Unraid variable set (timezone, shares, etc.) | — |
metrics | Live CPU % and memory usage | — |
services | Running services with name, online status, version | — |
display | Current UI theme name | — |
config | Config validity and error state | — |
online | Boolean reachability check | — |
owner | Owner username, avatar, profile URL | — |
settings | Unified settings key/value map | — |
server | Single-call summary: hostname, uptime, Unraid version, array state | — |
servers | All registered servers with LAN/WAN IPs and URLs | — |
flash | Flash drive vendor and product info | — |
ups_devices | All UPS devices with battery and power metrics | — |
ups_device | Single UPS device details | device_id |
ups_config | UPS daemon configuration | — |
health — 4 subactionsConnection and system health diagnostics.
| Subaction | Description | Required params |
|---|---|---|
check | Comprehensive health: API latency, array state, alerts, Docker container summary | — |
test_connection | Ping the Unraid API and return latency in ms | — |
diagnose | Subscription system status, error counts, reconnect state | — |
setup | Report credential status and print plugin/.env setup instructions | — |
array — 13 subactionsParity checks and array disk operations. Destructive subactions marked with *.
| Subaction | Description | Required params | Destructive |
|---|---|---|---|
parity_status | Current parity check progress, speed, errors | — | — |
parity_history | Past parity check results | — | — |
parity_start | Start a parity check | correct (bool) | — |
parity_pause | Pause a running parity check | — | — |
parity_resume | Resume a paused parity check | — | — |
parity_cancel | Cancel a running parity check | — | — |
start_array | Start the Unraid array | — | — |
stop_array | Stop the Unraid array | confirm=True | * |
add_disk | Add a disk to the array | disk_id; optional slot | — |
remove_disk | Remove a disk from the array (array must be stopped) | disk_id, confirm=True | * |
mount_disk | Mount an array disk | disk_id | — |
unmount_disk | Unmount an array disk | disk_id | — |
clear_disk_stats | Clear I/O statistics for a disk (irreversible) | disk_id, confirm=True | * |
disk — 6 subactionsShares, physical disks, log files, and flash backup. Destructive subactions marked with *.
Core homelab agents, commands, and setup/health skills for self-hosted service management. Includes interactive credential setup wizard and unified service health dashboard.
Connects Claude Code to the rustarr MCP server — one tool surface over a media-automation fleet (Sonarr, Radarr, Prowlarr, Tautulli, Overseerr, qBittorrent, SABnzbd, Plex, Jellyfin, and more). Also bundles standalone per-service skills (sonarr, radarr, prowlarr, overseerr, sabnzbd, qbittorrent, plex, jellyfin, tautulli, tracearr, bazarr) that drive each service's REST API directly as an offline fallback when the MCP server is unavailable.
Unraid NAS/homelab monitoring via MCP
SWAG reverse proxy configuration management via MCP. Create, edit, view, and manage nginx proxy configurations with auth integration.
Tailscale network management via MCP — query devices, ACL, DNS, users, and API keys from Claude
Best practices for monitoring and controlling an Unraid server through the Unraid Management Agent's MCP tools, diagnostic prompts, and REST API
Core homelab agents, commands, and setup/health skills for self-hosted service management. Includes interactive credential setup wizard and unified service health dashboard.
UniFi Network MCP server — manage network devices, clients, firewall, VPN, and more
Claude plugins for Datto RMM - devices, alerts, sites, jobs, remote monitoring
Monitor websites, APIs, and servers — create monitors, triage incidents, and query uptime stats from Claude Code. Supports HTTP, keyword, ping, port, heartbeat, DNS, API, and UDP monitors.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques