A
licenseA
qualityB
maintenanceEnables AI agents to drive Blender 5.1+ for modeling, sculpting, mesh editing, scene management, and rendering through live Python execution.
26
MIT
blender-mcp
by Mishaadevv
Related Servers
Alternatives to blender-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceEnables an AI agent to drive a live Blender session, building, sculpting, measuring, checking, rigging, lighting, rendering and exporting 3D models through safe operations in world units. Every geometry-changing call reports achieved dimensions, open edges and failures as numbers and review images, so modelling mistakes become visible instead of silent.113MIT
- AlicenseCqualityAmaintenanceEnables AI agents to control Blender through 150+ tools across 24 modules, including modeling, materials, lighting, animation, rendering, mesh quality analysis, and visual feedback, plus expert prompts and goal-first workflow management.209MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to fully control Blender through 50+ tools for 3D modeling, animation, materials, and scene management via HTTP endpoints.-
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to create, inspect, and animate 3D scenes in Blender through natural language and structured tool calls.6MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to control Blender 3D software through natural language, with tools for modeling, materials, animation, rendering, and rigging.3818MIT
TDQS
B3.1/5.0
Scored across 122 tools
Disambiguation2/5
Many tools overlap in purpose, especially the validation/diagnostic cluster (blender_validate, blender_auto_validate, blender_find_problems, blender_diagnose, blender_analyze_mesh), the material creation cluster (blender_create_material, blender_make_material, blender_procedural_material, blender_build_shader), and the render/capture cluster. Descriptions help but an agent still faces unclear boundaries when choosing among several plausible tools.
Naming Consistency4/5
Almost all tools use a consistent blender_ prefix and snake_case, making names predictable. The main weakness is that some names are noun-based (blender_geometry, blender_curves, blender_nla, blender_sequencer) while others are verb-based, but this is a minor deviation and still readable.
Tool Count1/5
With 122 tools, the surface is far too large for a coherent MCP toolset. Many related operations should be consolidated into fewer, more general tools, and the sheer count makes tool selection and discovery difficult for an agent.
Completeness4/5
The toolset covers an impressive breadth of Blender workflows: scene/object management, mesh editing, UVs, materials/shaders, textures, rendering, animation, physics, rigging, import/export, addons, packages, and asset libraries. A few lifecycle operations such as dedicated material deletion are missing, but the Python escape hatch and batch tool can work around gaps.
Maintenance
ActivityMaintained
ResponsivenessNo issues