# StudioMeyer Academy (npm · mcp-academy)

Free Memory-First AI Operator course as an MCP server. Bundled curriculum, no account needed.

- Trust score: 65/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.studiomeyer.academy`: 66/100, [markdown](https://verifymcp.io/servers/io-studiomeyer-academy/mcp.md), [page](https://verifymcp.io/servers/io-studiomeyer-academy/mcp)
- npm · `mcp-academy`: 65/100 (this document), [markdown](https://verifymcp.io/servers/io-studiomeyer-academy/mcp-academy.md), [page](https://verifymcp.io/servers/io-studiomeyer-academy/mcp-academy)

## Channel facts

- Registry: `npm`
- Package: `mcp-academy`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 63 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1007 tokens (~83/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 71% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add io-studiomeyer-academy -- npx -y mcp-academy
```

### Codex

```bash
codex mcp add io-studiomeyer-academy -- npx -y mcp-academy
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-studiomeyer-academy": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-academy"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-studiomeyer-academy --command npx --arg -y --arg mcp-academy
```

### Hermes

```yaml
mcp_servers:
  io-studiomeyer-academy:
    command: "npx"
    args: ["-y", "mcp-academy"]
```

### Other

```json
{
  "mcpServers": {
    "io-studiomeyer-academy": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-academy"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 65, +45)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-07-31 (score 20, −25)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (12)

### `academy_welcome` (~112 tokens)

ALWAYS call this first when a user connects or asks what this is. Returns a short orientation for StudioMeyer Academy — a free 6-level 'Memory-First AI Operator' curriculum (Levels 1-3 fundamentals, 4-6 memory/MCP/multi-agent), plus playbooks and build recipes. Read it back to the user in their language and offer to start at their level.

Input parameters:

- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.

### `academy_levels` (~61 tokens)

List the 6 curriculum levels with title, subtitle and lesson count. Use to show the user the learning path and ask where they want to start.

Input parameters:

- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.

### `academy_lessons` (~69 tokens)

List all lessons in a level (titles, descriptions, duration). No body — call academy_lesson for the full text.

Input parameters:

- `level` (number, required): Level 1-6
- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.

### `academy_lesson` (~106 tokens)

Get the FULL text of one lesson. Teach it to the user: explain it in your own words, answer questions, give examples. This is how a user 'takes the course' with you as tutor.

Input parameters:

- `level` (number, required)
- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.
- `slug` (string, required): Lesson slug, e.g. "01-was-ist-ai" (from academy_lessons)

### `academy_playbooks` (~75 tokens)

List hands-on playbooks (short, practical how-tos for Claude Code, MCP, memory, agents). Optional category filter.

Input parameters:

- `category` (string): Optional, e.g. "build", "use"
- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.

### `academy_playbook` (~50 tokens)

Get the full text of one playbook by slug.

Input parameters:

- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.
- `slug` (string, required)

### `academy_recipes` (~56 tokens)

List build recipes — step-by-step guides to build, deploy and ship real MCP servers and agent systems, organised by phase (1-16). Optional phase filter.

Input parameters:

- `phase` (number): Optional phase number 1-16

### `academy_recipe` (~26 tokens)

Get the full text of one build recipe by slug.

Input parameters:

- `slug` (string, required)

### `academy_search` (~87 tokens)

Search the whole curriculum (lessons + playbooks + recipes) by keyword. Returns ranked matches with snippets and ids. Use when the user asks about a topic and you want the most relevant material.

Input parameters:

- `limit` (number)
- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.
- `query` (string, required): Search keywords

### `academy_tutor_context` (~104 tokens)

Get a lesson packaged as a tutoring brief: the full lesson text plus its learning goals and the level context. Call this when the user wants to be *taught* a lesson — then YOU act as their tutor using this material (no Academy account needed, you are the tutor).

Input parameters:

- `level` (number, required)
- `locale` (string): Language. de=German, en=English, es=Spanish. Default en.
- `slug` (string, required)

### `search` (~44 tokens)

Search StudioMeyer Academy course material. Returns a list of matching lessons, playbooks and recipes with ids you can pass to `fetch`.

Input parameters:

- `query` (string, required): Search query

### `fetch` (~43 tokens)

Fetch the full text of one Academy item (lesson, playbook or recipe) by the id returned from `search`.

Input parameters:

- `id` (string, required): Item id from search results

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/io-studiomeyer-academy/mcp-academy#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 65
- 2026-08-01: 20
- 2026-07-31: 20
- 2026-07-30: 45
- 2026-07-28: 45
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/mcp-academy
- Socket report: https://socket.dev/npm/package/mcp-academy
- Repository: https://github.com/studiomeyer-io/mcp-academy
- Changelog RSS feed: https://verifymcp.io/servers/io-studiomeyer-academy/mcp-academy/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-studiomeyer-academy/mcp-academy/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-studiomeyer-academy/mcp-academy