Headless Blender automation via FastMCP — 41 portmanteau tools (150+ ops). Batch mesh/VSE/Grease Pencil, VRM, Gaussian splats; optional live bridge. For Cursor / Claude Desktop. React dashboard + Tauri app.
- capability exposure inferred + 35
- tool safety inferred + 7
- 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 6d ago · see ecosystem CVEs →
- C · 59 → C · 39
- C · 57 → C · 59
- C · 49 → C · 57
- C · 56 → C · 49
- A · 0 → C · 56
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 78f73ce · analyzer v33 · 5d ago
skills & prompt files 20
- agent-rules sandraschi-blender-mcp-78f73ce/.cursor/rules/architect.mdc
- skill sandraschi-blender-mcp-78f73ce/.cursor/skills/full-stack-developer/SKILL.md
- skill sandraschi-blender-mcp-78f73ce/.cursor/skills/mcp-server-developer/SKILL.md
- agent-rules sandraschi-blender-mcp-78f73ce/.cursorrules
- agent-rules sandraschi-blender-mcp-78f73ce/.github/copilot-instructions.md
- skill sandraschi-blender-mcp-78f73ce/.opencode/skills/blender-mcp/SKILL.md
- agent-rules sandraschi-blender-mcp-78f73ce/.windsurfrules
- agent-rules sandraschi-blender-mcp-78f73ce/AGENTS.md
- agent-rules sandraschi-blender-mcp-78f73ce/CLAUDE.md
- prompt-file sandraschi-blender-mcp-78f73ce/assets/prompts/3d_creation_assistant.md
- prompt-file sandraschi-blender-mcp-78f73ce/assets/prompts/system.md
- prompt-file sandraschi-blender-mcp-78f73ce/assets/prompts/user.md
- prompt-file sandraschi-blender-mcp-78f73ce/mcpb-packaging/prompts/advanced_workflow_templates.md
- prompt-file sandraschi-blender-mcp-78f73ce/mcpb-packaging/prompts/quick_start_templates.md
- prompt-file sandraschi-blender-mcp-78f73ce/mcpb/assets/prompts/3d_creation_assistant.md
- prompt-file sandraschi-blender-mcp-78f73ce/mcpb/assets/prompts/system.md
- prompt-file sandraschi-blender-mcp-78f73ce/mcpb/assets/prompts/user.md
- skill sandraschi-blender-mcp-78f73ce/skills/autonomous-modeling/SKILL.md
- skill sandraschi-blender-mcp-78f73ce/skills/blender-expert/SKILL.md
- skill sandraschi-blender-mcp-78f73ce/skills/pipeline-automation/SKILL.md
danger signals7
- dynamic code execution eval()/exec() sandraschi-blender-mcp-78f73ce/addon/blender_bridge_addon.py :318
exec(compile(code, "<mcp_bridge>", "exec"), {"bpy": bpy}) - dynamic code execution eval()/exec() sandraschi-blender-mcp-78f73ce/docs/blender_bridge_addon.py :318
exec(compile(code, "<mcp_bridge>", "exec"), {"bpy": bpy}) - dynamic code execution eval()/exec() sandraschi-blender-mcp-78f73ce/mcpb/assets/addon/blender_bridge_addon.py :318
exec(compile(code, "<mcp_bridge>", "exec"), {"bpy": bpy}) - dynamic code execution eval()/exec() sandraschi-blender-mcp-78f73ce/src/blender_mcp/handlers/atlasing_handler.py :484
atlas_found = eval(line.split(": ")[1]) - dynamic code execution eval()/exec() sandraschi-blender-mcp-78f73ce/src/blender_mcp/handlers/rigging_handler.py :799
unmapped = eval(line.split(": ")[1]) - dynamic code execution eval()/exec() sandraschi-blender-mcp-78f73ce/src/blender_mcp/handlers/shapekeys_handler.py :144
existing_keys = eval(line.split(": ")[1]) - dynamic code execution eval()/exec() sandraschi-blender-mcp-78f73ce/src/blender_mcp/handlers/vrm_metadata_handler.py :216
found_visemes = eval(line.split(": ")[1])
[](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.