Me Db — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Me Db (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.
Knowledge base service for the me-server frame: Silverbullet (web editor) plus an MCP server (markdown read/write/search for Claude) and a git-watcher that syncs the notes to your own private repo.
Notes live in your own private git repo (GITHUB_REPO), cloned on start and pushed on change.
me-db.<DOMAIN_BASE>:8443/ — Silverbullet; /mcp, /oauth/* — MCPme-db.<DOMAIN_BASE>:443/mcp — MCP (Claude.ai connector backend)auth.<DOMAIN_BASE>:8443 — OAuth browser popupDon't create top-level Silverbullet pages named mcp, oauth, register or health — they are shadowed by MCP routes.
Prebuilt by CI to ghcr.io/lidiaev/me-db-{mcp,watcher} (public; the VPS only pulls). Build your own with docker compose build.
Add a custom connector in Claude.ai (Settings -> Connectors): URL https://me-db.<DOMAIN_BASE>/mcp, OAuth, then enter the setup secret in the popup. The connector then works across Claude Code, Desktop and mobile.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.