Compiles structured specs into SCORM 1.2/2004 e-learning packages. 30 tools, quality gate, no LLM.
The Model Context Protocol (MCP) server compiles structured specifications into SCORM 1.2 and SCORM 2004 e-learning packages. It provides 30 tools and includes a quality gate. The server is described as having no LLM.
🛠️ Key Features
Compiles structured specs into SCORM 1.2 and SCORM 2004 packages
30 tools
Quality gate
No LLM
🚀 Use Cases
Converting structured learning specifications into SCORM 1.2 output
Converting structured learning specifications into SCORM 2004 output
Enforcing a quality check during package compilation
⚡ Developer Benefits
Fixed tool surface: 30 tools for SCORM compilation tasks
Deterministic behavior without an LLM
Quality gate support for structured-to-SCORM workflows
An MCP server that compiles interactive, standards-conformant e-learning courses.
You (or an AI client like Claude) are the author; this server is the compiler.
Describe a course as a structured spec — the server validates it, renders it, and packages it as a
self-contained SCORM zip that runs in any LMS (Moodle, SCORM Cloud, Rustici Engine, …).
Deterministic — no LLM runs on the server.
Four complete courses — four audiences, four visual identities — built entirely with this server
and served from a live deploy. Click any screenshot to launch.
Graduate level · argumentation theory · style-premium
Turkish · data literacy · inquiry-based (5E) · evidence-bound assessment
Each demo features a narrative thread, realistic artifact-mockup SVGs, flag-hunting simulations,
before/after comparisons, timelines, a case game, and adaptive feedback — with question-level SCORM
reporting underneath.
Why this exists
E-learning is usually hand-crafted in heavy desktop authoring tools. This project treats course
production as infrastructure for AI agents instead:
Zero-install authoring. Connect any MCP client to the hosted endpoint and start building —
no toolchain, no local setup. The client describes the course (objectives, screens, quizzes,
branching, media) over the Model Context Protocol; the server
does the hard part: validation, theming, accessible HTML rendering, the SCORM runtime bridge,
and packaging.
A quality gate that says no. AI can generate a lot of mediocre content fast. This server
pushes back: schema validation on every spec, an anti-slop lint (lint_course) whose error
tier blocks builds, and a CI proof chain (XSD + real SCORM Cloud imports + behavioral probe)
so that what ships actually works in an LMS — see Standards & evidence.
No vendor lock-in. Output is a plain SCORM 1.2/2004 zip with a self-contained player. MIT
licensed, self-hostable, and open to contributions.
Author = the MCP client · Compiler = this server.
A quiz screen rendered in the built-in slide-stage player
Quickstart
Option 1 — Hosted MCP (zero install)
Point any MCP client (Claude desktop/web/Code, Antigravity, …) at:
code
https://scorm.edumints.com/mcp
Sign in via OAuth or get an API key at the portal: https://mcp.edumints.com.
Then ask: "Build a 6-minute interactive course on X with a quiz and a summary." — you get a
downloadable SCORM zip back.
Works best together with the authoring skill (a Claude Agent Skill that teaches an AI client
how to author high-quality courses with this server):
https://github.com/kemalyy/edumints-scorm-skill
The image includes all optional features (ffmpeg, Node + HyperFrames for video, Piper TTS).
Apple Silicon + Docker Desktop: if the container crashes with Illegal instruction (SIGILL),
it is an upstream native-ARM64 issue in cryptography's Rust bindings
(pyca/cryptography#14733) — not this repo.
Workaround: run with --platform linux/amd64 (emulated).
Option 3 — Local (Python)
bash
python -m venv .venv && source .venv/bin/activate
pip install ".[tts]"# ".[tts]" adds offline Turkish TTS (Piper); drop it if unwanted
python server.py # serves MCP over HTTP
For video generation also install Node 22+ with HyperFrames (npm i -g hyperframes) plus ffmpeg.
Configuration: copy .env.example and adapt (data dir, quotas, base URL, TTLs). No secrets are
required to run locally.
Example
A course is produced from a single build_from_spec call (this is examples/small.json, abridged):
json
{"title":"Intro to SCORM","scorm_version":"1.2","language":"en","tracking":{"completion_rule":"viewed_all_and_passed","passing_score":50},"screens":[{"type":"title_slide","id":"t1","title":"Intro to SCORM","subtitle":"Core concepts in 5 minutes"},{"type":"content_slide","id":"c1","title":"What is SCORM?","body_html":"<p><strong>SCORM</strong> lets e-learning content talk to an LMS.</p>"},{"type":"mcq","id":"q1","title":"Mini quiz","prompt_html":"<p>What is SCORM for?</p>","options":[{"id":"a","text_html":"Content–LMS communication","correct":true},{"id":"b","text_html":"Video editing"}],"points":10},{"type":"summary","id":"s1","title":"Well done","body_html":"<p>You learned the basics.</p>"}]}
Composable game engine — the game screen composes mechanic primitives
(score/lives/timer/hints) + declarative when event if condition then action rules + branching
nodes; adaptive_practice estimates proficiency (Elo or Bayesian Knowledge Tracing) and
calibrates difficulty per learner. See docs/GAME-PATTERNS.md.
Slide-stage player — fixed 16:9 stage scaled to every screen, player bar
(play/seekbar/captions/menu/replay), narration-synced timed timelines, section-grouped menu,
fully responsive, inline SVG icons. i18n shell (tr/en) with RTL support.
Real SCORM tracking — cmi.interactions (question-level reporting), cmi.objectives,
adlcp:masteryscore (1.2) / completionThreshold (2004), LOM metadata, and a compact
suspend-data v2 encoding for resume state.
Theming — style presets (style-minimal / style-playful / style-premium, and more)
layered with brand tokens: one style, many brands. Light/neutral/high-contrast presets,
WCAG-aware, prefers-reduced-motion support.
Quality gates — anti-slop lint with a blocking error tier, plus game accessibility audits.
Media — cross-MCP asset import (add_asset via data-URI or https), ffmpeg processing,
programmatic motion-graphic/data-viz video (HyperFrames), built-in offline Turkish TTS (Piper).
Telemetry — optional xAPI statements from the player; cmi5 is partial (launch
detection only — no cmi5.xml packaging yet). See docs/GAME-XAPI.md.
QTI 2.1 export — quiz screens export as QTI assessmentItems for interop with assessment
platforms. See docs/QTI.md.
Claims are cheap; this repo ships its proof chain in CI:
XSD conformance — generated imsmanifest.xml files are validated against the official
ADL/IMS schemas for both SCORM 1.2 and 2004 (automated in tests/test_conformance.py).
Real SCORM Cloud round-trip — CI imports built packages into actual
SCORM Cloud via its REST API: 4/4 combinations
(small/rich × 1.2/2004) must import with 0 parser warnings and produce a launchable
registration. This is a blocking gate, not an advisory check.
Behavioral probe — scorm-probe launches built courses in real Chromium against a fake
LMS and asserts runtime behavior (init, navigation, scoring, completion). Also blocking in CI;
a silent skip fails the build.
Anything else — mirror repos, re-uploaded zips, PyPI/npm packages, other registries or domains —
is unofficial and unverified. We publish no PyPI or npm packages today. If you find a
lookalike, please report it via SECURITY.md.
