Schulcloud-MCP/docs/DEPLOYMENT.md

Deployment

The shape of it

claude.ai  ──HTTPS──┐
                    ├─▶ VPS (public IP) ──tunnel──▶ Pi 5 (home network)
schulcloud CLI ─────┘                                └─ Caddy ─▶ schulcloud-mcp:8080
                                                                  ├─ /mcp      (Claude)
                                                                  ├─ /api      (CLI)
                                                                  ├─ Postgres  (index)
                                                                  ├─ mirror    (file bytes)
                                                                  └──▶ schulcloud-thueringen.de

Both front ends use the same hostname and the same bearer token. /mcp speaks MCP; /api serves the CLI's manifest, file bytes and re-crawl requests.

Claude's custom connectors call the endpoint from Anthropic's cloud, so it must be publicly reachable over real TLS — a localhost tunnel or self-signed cert will not do. The VPS provides the public address; Caddy on the Pi terminates TLS and obtains the certificate.

The container publishes no host port. Caddy reaches it over the shared Docker network, so the only way in from the internet is through Caddy and then through this server's bearer check.

First deploy

git clone <this repo> /opt/schulcloud-mcp
cd /opt/schulcloud-mcp

cp .env.example .env
# Fill in TSC_URL and TSC_JWT_COOKIE (see docs/AUTH.md), then:
openssl rand -hex 32   # → MCP_AUTH_TOKEN

docker compose up -d --build
docker compose logs -f schulcloud-mcp

Expect:

[schulcloud-mcp] listening on 0.0.0.0:8080 — instance https://… , auth enabled, keepalive every 30min

auth DISABLED there means MCP_AUTH_TOKEN is empty — fix it before exposing the service. A keepalive: token rejected (401) line right after startup means the Schulcloud token is dead and needs replacing (see docs/AUTH.md); the server will run but every tool will fail.

Joining the existing Caddy

The Pi already runs Caddy and PostgreSQL in a Compose project. This server needs neither a database nor its own Caddy — only a network it shares with the existing one.

Find the network Caddy is on:

docker inspect -f '{{range $k,$v := .NetworkSettings.Networks}}{{$k}}{{"\n"}}{{end}}' <caddy-container>

Then in docker-compose.yml, set that name and mark it external:

networks:
  caddy:
    external: true
    name: <the network name you just found>

Postgres

The index needs a database. On the Pi, use the existing PostgreSQL rather than the container in docker-compose.yml — create a database and user for it:

CREATE USER schulcloud WITH PASSWORD '…';
CREATE DATABASE schulcloud OWNER schulcloud;

Then set DATABASE_URL in .env and delete the postgres service from the compose file. Migrations run automatically at startup; pg_trgm is created by the first migration, which needs the database owner to be able to CREATE EXTENSION.

Without DATABASE_URL the server still runs: search crawls live on every call and /api returns 503. The startup log says which mode it is in.

Caddy

Append deploy/Caddyfile.snippet to the Pi's Caddyfile, replacing mcp.example.org with the real hostname, and reload:

docker exec <caddy-container> caddy reload --config /etc/caddy/Caddyfile

Two settings in that snippet matter and are easy to miss:

• flush_interval -1 — MCP's Streamable HTTP transport holds a server-sent-events channel open. Without this, Caddy buffers it and the connector hangs with no error.
• read_timeout/write_timeout of 300s — a search call walks every course and can take tens of seconds. Caddy's defaults will cut it off.

Ports and DNS

• DNS for the hostname points at the VPS, not the Pi.
• The VPS forwards 80 and 443 to the Pi's Caddy. Port 80 must work too, or Caddy cannot complete the ACME HTTP challenge.
• Nothing else needs to be exposed.

Verifying from outside

curl -s https://mcp.example.org/healthz
# {"status":"ok","sessions":0}

curl -s -o /dev/null -w '%{http_code}\n' -X POST https://mcp.example.org/mcp \
  -H 'content-type: application/json' -d '{}'
# 401   ← the bearer check is live

If /healthz answers but /mcp returns 401 with a correct token, check that the token in .env matches the one in the connector exactly — no trailing newline from a copy-paste.

Connecting Claude

1. claude.ai → Settings → Connectors → Add custom connector.
2. URL: https://mcp.example.org/mcp
3. Under Advanced settings, add the bearer token as an authorization header. If your organisation has no header-auth field, the server also accepts the token as X-Api-Key.
4. Enable the connector in a conversation via + → Add connectors.

Ask "which courses am I in?" as a first check — that exercises auth, the Schulcloud token and the API in one call.

Running it locally instead

For Claude Code or Claude Desktop on your own machine, skip all of the above and use stdio:

{
  "mcpServers": {
    "schulcloud": {
      "command": "node",
      "args": ["/path/to/schulcloud-mcp/dist/bin/stdio.js"],
      "env": {
        "TSC_URL": "https://schulcloud-thueringen.de",
        "TSC_JWT_COOKIE": "…"
      }
    }
  }
}

MCP_AUTH_TOKEN is irrelevant in stdio mode — there is no network listener.

Updating

cd /opt/schulcloud-mcp && git pull
docker compose up -d --build
docker compose exec schulcloud-mcp node -e "1" # sanity
npm run probe                                  # re-verify the API assumptions

Operational notes

• Restart policy is unless-stopped; the container comes back after a reboot.
• Sessions are in-memory and dropped after 30 minutes idle. A restart invalidates them; Claude re-initializes transparently.
• Logs are capped at 3 × 10 MB. The Authorization header is never logged.
• The container is read-only with cap_drop: ALL and no-new-privileges, running as the unprivileged node user. The one writable path is the mirror volume at /data/mirror, which holds downloaded file bytes; everything else stays read-only.
• The mirror grows. It holds a copy of every course file under MIRROR_MAX_BYTES (64 MiB default). Larger files — videos, mostly — are indexed as metadata and proxied live on request instead. Budget a few GB.
• A re-crawl of unchanged content downloads nothing, because Schulcloud file records are immutable, so the 6-hourly crawl costs a few hundred cheap GETs in the steady state.
• The Schulcloud session has a 2-hour sliding TTL, so the server calls refresh-session every 30 minutes. Watch for keepalive: session extended, 7200s in the logs, or run npm run keepalive-status for a summary.
• Never leave a Schulportal tab open on the token you deployed. It shares the session and its auto-logout will revoke it ~2h after login. Copy the cookie in a private window and close it — see docs/AUTH.md.
• Downtime longer than two hours lapses the session and restarting does not recover it: a long power cut means pasting a fresh TSC_JWT_COOKIE.
• Monthly chore: refresh TSC_JWT_COOKIE before its 30-day hard expiry. npm run probe reports both clocks.