Blender 3D automation via FastMCP 3.2 — 41 portmanteau tools, 150+ operations. AI construction, VRM avatars, Gaussian splats, VSE video editing, Grease Pencil 2D animation, Tauri 2.0 desktop. React dashboard.
- capability exposureinferred+35
- recent driftinferred+12
- tool safetyinferred+12
- trust mitigatorsmixed−3
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 14m ago · see ecosystem CVEs →
- A · 0 → C · 56
no known CVEs for this server.
- highdangerous code
dynamic exec: eval()/exec()
analyzed commit c02154b · analyzer v17 · 58m ago
skills & prompt files 16
- agent-rulessandraschi-blender-mcp-c02154b/.cursor/rules/architect.mdc
- skillsandraschi-blender-mcp-c02154b/.cursor/skills/full-stack-developer/SKILL.md
- skillsandraschi-blender-mcp-c02154b/.cursor/skills/mcp-server-developer/SKILL.md
- agent-rulessandraschi-blender-mcp-c02154b/.cursorrules
- agent-rulessandraschi-blender-mcp-c02154b/AGENTS.md
- agent-rulessandraschi-blender-mcp-c02154b/CLAUDE.md
- prompt-filesandraschi-blender-mcp-c02154b/assets/prompts/3d_creation_assistant.md
- prompt-filesandraschi-blender-mcp-c02154b/assets/prompts/system.md
- prompt-filesandraschi-blender-mcp-c02154b/assets/prompts/user.md
- prompt-filesandraschi-blender-mcp-c02154b/mcpb-packaging/prompts/advanced_workflow_templates.md
- prompt-filesandraschi-blender-mcp-c02154b/mcpb-packaging/prompts/quick_start_templates.md
- prompt-filesandraschi-blender-mcp-c02154b/mcpb/assets/prompts/3d_creation_assistant.md
- prompt-filesandraschi-blender-mcp-c02154b/mcpb/assets/prompts/system.md
- prompt-filesandraschi-blender-mcp-c02154b/mcpb/assets/prompts/user.md
- skillsandraschi-blender-mcp-c02154b/skills/autonomous-modeling/SKILL.md
- skillsandraschi-blender-mcp-c02154b/skills/pipeline-automation/SKILL.md
danger signals6
- dynamic code executioneval()/exec()sandraschi-blender-mcp-c02154b/mcpb/src/blender_mcp/handlers/scripting_handler.py:144
exec(_code, _script_globals, _script_locals) - dynamic code executioneval()/exec()sandraschi-blender-mcp-c02154b/src/blender_mcp/handlers/atlasing_handler.py:460
atlas_info = eval(mesh["material_atlas"]) - dynamic code executioneval()/exec()sandraschi-blender-mcp-c02154b/src/blender_mcp/handlers/rigging_handler.py:799
unmapped = eval(line.split(": ")[1]) - dynamic code executioneval()/exec()sandraschi-blender-mcp-c02154b/src/blender_mcp/handlers/scripting_handler.py:145
exec(_code, _script_globals, _script_locals) - dynamic code executioneval()/exec()sandraschi-blender-mcp-c02154b/src/blender_mcp/handlers/shapekeys_handler.py:144
existing_keys = eval(line.split(": ")[1]) - dynamic code executioneval()/exec()sandraschi-blender-mcp-c02154b/src/blender_mcp/handlers/vrm_metadata_handler.py:216
found_visemes = eval(line.split(": ")[1])
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:sandraschi/blender-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 sandraschi.