A Drupal-shaped content store — title, body, datetime, taxonomy — that models write to over MCP. One Cloudflare Worker, one D1, one click. OAuth for claude.ai.
- capability exposure inferred + 35
- tool safety inferred + 5
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 2d ago · see ecosystem CVEs →
- B · 20 → C · 37
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed commit ff5b5cd · analyzer v33 · 2d ago
danger signals1
- dynamic code execution new Function() Soul-Brews-Studio-digger-node-ff5b5cd/test/app.test.ts :915
expect(() => new Function(source)).not.toThrow();
[](https://mcpobservatory.com/servers/github:Soul-Brews-Studio/digger-node/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of Soul-Brews-Studio.