Persistent memory and knowledge graph for AI agents via MCP — PostgreSQL + pgvector + Ollama
- capability exposureinferred+14
- recent driftinferred+20
- tool safetyinferred+12
inferred
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.
graded 12m ago · see ecosystem CVEs →
- C · 48 → C · 46
- C · 40 → C · 48
No known CVEs for this server.
- highdangerous code
dynamic exec: eval()/exec()
analyzed commit 61fe7c9 · analyzer v18 · 1h ago
skills & prompt files 1
- agent-rulesvicquick-nobrainr-61fe7c9/CLAUDE.md
danger signals1
- dynamic code executioneval()/exec()vicquick-nobrainr-61fe7c9/src/nobrainr/db/schema.py:462
-- Extraction eval (qwen3.6 vs qwen3.5 A/B, LLM-judge self-scored).
- recent drift+20 capability drift →
[](https://mcpobservatory.com/servers/github:vicquick/nobrainr/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 vicquick.