Blender
Natural-language control of Blender for 3D scene creation, manipulation, and rendering.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Blender, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Blender MCP connects an agent to a running Blender instance so it can create and manipulate 3D scenes, import assets, and render — all via natural language, without knowing Blender's Python API. It executes Python inside Blender to fulfill requests. That embedded code-execution path is the notable security surface, since agent-generated scripts run with Blender's local privileges.
Key features and capabilities
- Natural-language 3D scene control
- Runs Python inside Blender
- Asset import and rendering
- No Blender API knowledge needed
Use cases
- AI-assisted 3D modeling
- Procedural scene generation
- Automated rendering workflows