Files

MechaCat02 10c6544579 Prepare for a live account: separate the indexes, and probe new routes live

With .env pointing at the real account, testing against the local instance
became dangerous: process env beats --env-file, so a local smoke run would
crawl fixtures straight into the live index, where a per-course refresh
carries them forward indefinitely. mcp-env.sh now pins its own database
(schulcloud_local) and mirror as well as the instance.

The override publishes the server on MCP_HOST_PORT and takes
CRAWL_INTERVAL_MS from .env, since what_changed can only report what
happened between crawls. The build context leaves out tmp/, which holds a
mirror of the account's files, and local-instance/.

probe checks live what the gap fixes established locally: the /api/v1 course
and user routes, classes, room allowedOperations as an object, and the
preview enums on a real file. A failure there means a feature degrades
rather than breaks.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-16 20:19:16 +02:00

4.5 KiB

Raw Blame History

Running it locally

Everything runs on your machine: Postgres, the server, the CLI, and Claude Code talking to all of it. Only Schulcloud itself is remote.

Start the stack

cp .env.example .env     # fill in TSC_URL, TSC_JWT_COOKIE, MCP_AUTH_TOKEN
npm install && npm run build
docker compose up -d --build
curl -s http://127.0.0.1:8080/healthz     # {"status":"ok","sessions":0,"index":"on"}

docker-compose.override.yml is merged automatically and is local-only: it publishes the server on 127.0.0.1:8080 and Postgres on 127.0.0.1:55432, and switches crawling to on-demand. Two .env settings adjust it: MCP_HOST_PORT moves the published port when 8080 is taken, and CRAWL_INTERVAL_MS restores a crawl timer — worth doing against a real account, because what_changed can only report what happened between crawls.

After pasting a new TSC_JWT_COOKIE into .env, recreate the container — env_file is read when the container is created, not on restart:

docker compose up -d --force-recreate schulcloud-mcp
``` On the Pi neither port is published — Caddy
reaches the container over the Docker network.

Loopback binding is deliberate. The bearer token is the only thing in front of
your account's data, so it should not be listening on your LAN while you test.

## Populate the index

A full crawl is ~270 requests; start with one course:

```bash
node dist/bin/cli.js login --server http://127.0.0.1:8080 --token "$MCP_AUTH_TOKEN"
node dist/bin/cli.js refresh --course <courseId>    # or omit --course for everything
node dist/bin/cli.js status

Get a course id from curl -s -H "Authorization: Bearer $TSC_JWT_COOKIE" \ "$TSC_URL/api/v3/courses?limit=5" | jq -r '.data[] | "\(.id) \(.title)"'.

Connect Claude Code

Claude Code supports MCP over stdio, SSE and HTTP. The VS Code extension runs the same Claude Code underneath, so it reads the same configuration — register once and both work.

Use --scope user. Claude Code's default scope is local, which is per-project: the server is stored under that directory in ~/.claude.json and claude mcp list will not show it from anywhere else. Since the point is to ask about your coursework from wherever you happen to be, user scope is what you want. (project scope would write a .mcp.json into the repo — wrong here, because the HTTP config carries a token.)

HTTP — matches the deployed setup:

claude mcp add --scope user --transport http schulcloud http://127.0.0.1:8080/mcp \
  --header "Authorization: Bearer $MCP_AUTH_TOKEN"

stdio — no server or Docker needed:

claude mcp add --scope user schulcloud-stdio \
  -e DATABASE_URL=postgresql://schulcloud:schulcloud@127.0.0.1:55432/schulcloud \
  -- node --env-file=/absolute/path/to/.env /absolute/path/to/dist/bin/stdio.js

--env-file keeps the JWT in .env rather than copying it into the MCP config. The HTTP form has no equivalent — its header holds the token — so that token lives in ~/.claude.json.

Check it:

claude mcp list       # schulcloud: http://127.0.0.1:8080/mcp (HTTP) - ✔ Connected
claude mcp get schulcloud

If claude mcp list does not show it, the usual cause is scope: run claude mcp list from the directory you added it in, and if it appears there, re-add it with --scope user.

Then just ask: "which courses am I in?", "what's due this week?", "find the material about Verschlüsselung". Inside a session, /mcp lists the servers and their tools.

Test the CLI

node dist/bin/cli.js ls --long
node dist/bin/cli.js sync --dry-run        # shows what it would mirror
node dist/bin/cli.js sync

npm link puts it on your PATH as schulcloud.

Run the test suites

npm test              # 58 offline tests
npm run smoke         # end-to-end against the live instance, live-only mode
DATABASE_URL=… npm run smoke    # end-to-end with the index (34 checks)

Store tests need a database and skip without one:

docker exec schulcloud-mcp-db psql -U schulcloud -d schulcloud \
  -c "CREATE DATABASE schulcloud_test OWNER schulcloud"
TEST_DATABASE_URL=postgresql://schulcloud:schulcloud@127.0.0.1:55432/schulcloud_test npm test

These tests TRUNCATE. They refuse to run unless the database name contains "test", because aiming them at the dev database once was enough — the fixtures ended up in real data.

Tearing down

docker compose down          # keep the index and mirror
docker compose down -v       # discard them too
claude mcp remove schulcloud

4.5 KiB Raw Blame History