Production-shaped MCP server for Blender with goal-first routing, curated tools, deterministic verification, and vision-assisted 3D modeling workflows.
Source not yet analyzed — this grade rests on attested signals (CVEs, supply-chain) only. It is a floor: reading the code could raise it, not lower it.
- capability exposureinferred+35
- recent driftinferred+12
- tool safetyinferred+12
- trust mitigatorsmixed−8
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 16m ago · see ecosystem CVEs →
- A · 0 → C · 51
No known CVEs for this server.
- highdangerous code
dynamic exec: __import__()
analyzed analyzer v18 · 8h ago
skills & prompt files 1
- agent-rulesPatrykIti-blender-ai-mcp-4325315/AGENTS.md
danger signals1
- dynamic code execution__import__()PatrykIti-blender-ai-mcp-4325315/server/adapters/mcp/contracts/__init__.py:33
module = __import__(module_name, fromlist=[name])
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:PatrykIti/blender-ai-mcp/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 PatrykIti.