Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An MCP (Model Context Protocol) server that connects Claude Cowork to a PostgreSQL database, enabling course navigation (course → unit → chapter → lesson) and LaTeX quiz file import. Parsed quiz questions are inserted into the dim_questions and dim_options tables linked to lessons via dim_tests.
api schemacd mcp-server
npm install
cp .env.example .env
# Edit .env with your real DATABASE_URL
npx drizzle-kit pull # generates src/db/schema.ts from live DB
npm run devAdd MCP server URL: http://localhost:3100/mcp
| Tool | Description |
|---|---|
get_courses | Fetch all available courses |
get_units_with_chapters | Fetch units and chapters for a course |
get_lessons | Fetch lessons for a chapter |
import_quizzes | Parse a LaTeX file and insert quiz questions for a lesson |
Each question uses a \question macro with 4 brace-delimited arguments:
\question
{Question text here}
{\item choice1\item choice2\item choice3\item choice4}
{Explanation (ignored)}
{A) choice1}api schema (not public)dim_questions + dim_options (normalized), not a flat tabledim_test, one is created automatically during import~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.