# school.delegation/delegation-school

> Learn to delegate real work to AI, not just chat with it — a course taught live in your own Claude.

- name: school.delegation/delegation-school
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 75/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/school.delegation%2Fdelegation-school
- tools: https://api.protogrid.dev/v1/servers/school.delegation%2Fdelegation-school/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "delegation-school": {
      "type": "http",
      "url": "https://delegation.school/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-97% ~updated-133d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_lessons (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); course_stats (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); start_session (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,304 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 9, about 1,304 tokens to load them all
- tool set hash: b2b18f4271ebcaa20e3038aeeebbc356
- badge: [![protogrid quality](https://protogrid.dev/badge/school.delegation/delegation-school.svg)](https://protogrid.dev/servers/school.delegation/delegation-school)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://delegation.school/mcp (streamable-http, auth none, reachable true, uptime30d 0.974359)

## Packages

_none_

## Tools (9)

- `complete_lesson`: Record a lesson result for a learner AFTER grading its quiz/assignment. passed:true marks it done and advances; passed:false records the attempt without advancing (reteach). Always include a `reflection` when you have one — it's the signal that improves the course.
- `course_stats`: OPERATOR / Inspectable State: usage snapshot of the whole course — learner count, level mix, completions, per-lesson pass rates, and recent reflections. Requires admin_key. Answers 'what is the state of the work?' for an operator agent.
- `get_lesson`: Get the full markdown of one lesson by slug. Teach from it: lead with the why, then run the exercise with the learner's real work.
- `list_lessons`: List lessons (slug, title, track, order, summary), optionally filtered to one track.
- `overview`: What delegation.school is, the three tracks, and how to run the course as the learner's tutor. Background reading.
- `set_level`: OPERATOR: reclassify an existing learner's track (scratch | intermediate | power). Routes through the learner's record so the change sticks. Use when a learner was placed wrong — e.g. a scratch enrollee who's really a power operator. Requires admin_key. The learner must have started a session first.
- `start_session`: Call FIRST. Place or resume a learner: returns their level, completed lessons, and the recommended next lesson. Ask for the learner's EMAIL ADDRESS and pass it as `learner` — emails are stable and unique; a bare name collides across learners and gets mistyped. Pass their real name as `name` for the certificate.
- `submit_feedback`: Send the course team feedback FOR the learner — what's confusing, a bug, an idea, or praise. No grade, no admin key. Use it the moment a learner is stuck or reacts to something, AND always offer it when a session wraps ('anything confusing, or that you wish it did?'). Routes to the team's Slack + the feedback log so friction becomes a signal instead of a 1:1 text.
- `verify_ticket`: OPERATOR (Capital Factory gift shop): validate a reward code (Golden Ticket GT- or Founding Graduate badge FG-) — returns who earned it, the reward, when, and whether it's been redeemed. Pass redeem:true to mark it redeemed at point of redemption. Requires admin_key.