Give your AI tools architecture-aware reasoning. Knowledge graph from any codebase — 14 LLM backends, impact analysis, confidence scores. Works with Claude Code, Cursor, VS Code Copilot.
- capability exposureinferred+35
- recent driftinferred+20
- tool safetyinferred+12
- trust mitigatorsmixed−11
inferredmixed
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 2m ago · see ecosystem CVEs →
No known CVEs for this server.
- highdangerous code
dynamic exec: pickle.loads(), __import__()
analyzed commit df14608 · analyzer v20 · 21h ago
skills & prompt files 1
- agent-rulesquantamixsol-graqle-df14608/CLAUDE.md
danger signals2
- dynamic code executionpickle.loads()quantamixsol-graqle-df14608/graqle/calibration/methods.py:322
inst._model = pickle.loads(Path(path).read_bytes()) # noqa: S301 - dynamic code execution__import__()quantamixsol-graqle-df14608/scripts/debate_evidence.py:41
getattr(__import__(mod, fromlist=[name]), name)
- recent drift+20 capability drift →
[](https://mcpobservatory.com/servers/github:quantamixsol/graqle/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 quantamixsol.