Provides read-only Docker container monitoring and diagnosis: lists containers with state, image, project, and ports; retrieves container details, restart and exit information, mounts, and redacted logs; diagnoses crash loops, permission issues, port conflicts, missing bind folders, resource problems, restart policy issues, and image/security concerns.
Provides NAS health and administration visibility for Synology systems, including model/DSM version, uptime, temperature, CPU and memory, disk SMART health, storage pools and volumes, backup target status, security scan status, and read-only access to allowed folders and files.
Integrates Watchtower update history so the server can report what Watchtower updated or stopped and when, correlate container stoppages or breakage with recent updates, and suggest rollback when problems begin after an update.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
An MCP server that lets Claude look after a Synology NAS: system health, disks and volumes, Docker containers (state, logs, diagnosis), Watchtower update history, backups, and the NAS gate security scan.
Stage 1a: read-only, home network only. Nothing here can change the NAS: Docker is reached through a socket proxy with POST disabled, and mounted folders are read-only.
Tool | What it answers |
| How is the NAS? (everything below, summarised) |
| Model, DSM version, uptime, temperature, CPU, memory |
| Disks (SMART, temperature, bad sectors), pools, volumes |
| Every container with state, image, project, ports |
| One container: exit code and meaning, restarts, mounts, last update |
| The container's log, secrets redacted |
| Problems and suggested fixes (see below) |
| What Watchtower updated or stopped, and when |
| Starts, stops, crashes, OOM kills, pulls and updates over time |
| Newest file per backup target, late or not |
| From the NAS gate, if configured |
| Allowed folders only |
container_diagnose findscrash loops and errors that repeat in the log
containers stopped with no visible cause, matched against Watchtower's own log (Container Manager does not show what Watchtower does)
breakage that started right after a Watchtower update, with a rollback suggestion
permission errors (suggests user: "1026:100"), ports in use, missing bind folders,
options a new version removed, wrong architecture, full disk, out of memory
no restart policy, standalone containers (suggests a Compose project), :latest tags
services without a password, privileged mode, unmaintained images
Docker forgets past events when it restarts, so a small recorder keeps its
own log in data/events.jsonl for nas_timeline.
Related MCP server: MCP SSH SRE
Create a DSM administrator user for the server (2-step verification off for it).
Create the folder /volume1/docker/nas-mcp and inside it a folder data.
Put docker-compose.yml in it, .env.example as .env, and
config.example.yaml as data/config.yaml; fill them in.
Container Manager → Project → Create → path /volume1/docker/nas-mcp.
Open http://<nas>:8790/?token=<your token> for the status page.
Everything specific to one NAS lives in data/config.yaml and .env,
never in this repository.
1b: OAuth and a public address (Tailscale Funnel or Cloudflare Tunnel) for Claude
1c: write tools behind an "MCP" window in the NAS gate, phone approval for
destructive actions, nothing ever deleted (renamed _to_delete_…)
1d: post-update checks with a one-tap rollback, NAS health scan
2: media apps (Seerr, Radarr, Sonarr, Jellyfin)
pip install -r requirements.txt pytest
python -m pytest -qThis server cannot be deployed
Read-only server insight: why a Linux server or K8s cluster is slow, failing or changed.
Read-only local AI advice, shared reports and website audits. No PC scan or local actions.
Read-only AI access to HAVN properties, leads, tasks, files, media, and analytics.
Give Claude only the Google Drive files you choose. Every action logged.
