convez.ai
MCP ServerAutomaçãoAvançado
sandraschi

Blender MCP — Automação 3D via IA

sandraschi/blender-mcp

Crie 3D complexo em Blender descrevendo em português natural

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que automatiza Blender 3D através de linguagem natural, permitindo criar cenas, malhas, materiais e animações via Claude. Oferece 41+ ferramentas portmanteau cobrindo exportação (GLB/GLTF/FBX/VRM), renderização, edição de vídeo (VSE), animação 2D (Grease Pencil) e splats Gaussianos. Funciona em modo headless (padrão) ou com interface gráfica ao vivo via addon bridge.

Instalação

$npx convez-ai sandraschi/blender-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
67
Forks
14
Acompanhando
0
Saúde
42%
Último commit
há 2 semanas
Versão
v0.11.1
Issues abertas
2
Contribuidores
2

Casos de uso

  • Geração automática de avatares VRM para VRChat
  • Exportação em lote de assets 3D (GLB/GLTF/FBX/OBJ/USD)
  • Criação de cenas e animações descritas em linguagem natural
  • Integração em pipelines CI/CD para renderização e exportação headless
  • Edição de vídeo (VSE) e animação 2D (Grease Pencil) programáticas

Veredito

Ferramenta robuusta e bem arquiteturada para automação 3D em escala, com suporte a múltiplos formatos de saída e integração em pipelines downstream (Godot, Unity, VRChat). Requer instalação independente do Blender e conhecimento técnico para melhorar, mas reduz drasticamente tempo de iteração em workflows 3D repetitivos.

README

A tradução para o português deste README ainda está na fila.

Blender MCP — AI-Powered Blender Automation

Control Blender with natural language through MCP. Tell Claude to create a steampunk robot with glowing eyes and watch it build in Blender.

How it runs

ModeHost appWhen
Headless (default)blender --background subprocessBatch export, CI, agents without a display; VSE, geonodes, most mesh ops
Live GUI (optional)Blender + bridge addonWatch the agent build; viewport screenshots; sculpt with live feedback
Per-tool overrideprefer_session=FalseBatch jobs force headless even if bridge is connected

You do not need to open Blender’s UI for most MCP tools — the server spawns headless Blender automatically and falls back from live session when no bridge is connected.

Install Blender separately; it is never bundled. Override path with BLENDER_EXECUTABLE.

Watch or batch — Most tools run headless Blender. Use blender_session start + enable the bridge addon only if you want the viewport to update live while the agent works. See INSTALL.md.

Hands-in / Hands-out

DirectionArtifactsNotes
Hands-inNatural-language scene promptsAgent instructions; blender_ai_* script generation
Hands-in.blend, image refs, mesh filesWebapp upload or tool params
Hands-inRodin / Tripo / Hunyuan mesh URLsblender_ai_generate and related tools
Hands-inInline bpy scriptsblender_script_execute, handler-backed tools
Hands-out.glb, .gltf, .fbx, .obj, .usdblender_export — headless
Hands-out.vrm, VRChat-ready avatarsExport + validation pipeline — headless
Hands-out.blend (saved scene)After agent edit session — headless or live bridge
Hands-outViewport PNG, MP4 (VSE), Gaussian splatsblender_render, blender_vse, splat tools — headless

Fleet pipelines (downstream)

Downstream MCPTakes from blender-mcp
godot-mcp.glb / .gltf game assets
vrchat-mcp.vrm after validation
tahoma2d-mcpRendered image sequences / GP output
freecad-mcp.step via intermediate export
unity3d-mcp.fbx / .glb for Unity import

Features

  • Natural-language 3D creation — scenes, meshes, materials, lighting, animation
  • Live GUI bridge — watch the agent build in Blender while you chat
  • 48+ MCP tools — mesh edit, sculpt, geonodes, compositor, VSE, export (GLB, VRM, VRChat, Unity)
  • Generative AI hooks — Rodin/Tripo/Hunyuan mesh generation and vision refine
  • Webapp dashboard — scene explorer, agent lab, materials, mesh/splat pipeline
  • Fleet-ready — FastMCP 3.2, .mcpb packaging, Prometheus metrics, optional Docker

Quick Install

  1. Download blender-mcp-*.mcpb from Releases
  2. Drag it into Claude Desktop

Done. Install Blender separately if you have not already.

Other methods (npx mcpb, manual config, developer setup): INSTALL.md

What You Can Do

Try these in Claude Desktop after install:

Create a red cube on a gray floor with a sun lamp and render a viewport screenshot.

Build a simple chair with wood material and export as GLB.

Start a live Blender session and add a sphere with a metallic blue shader.

Documentation

DocContents
InstallationAll install methods, prerequisites, bridge setup
ConfigurationEnv vars, Claude Desktop env block
Tool ReferenceCapabilities and tool catalog
DevelopmentContributing, just, lint, build
TroubleshootingCommon errors and fixes
ArchitectureSystem design
RoadmapPlanned improvements
MonitoringPrometheus / Grafana / Loki
DockerOptional container deploy

Extended guides: docs/DOCUMENTATION_INDEX.md

Webapp and Native App

Dashboard (optional): .\start.ps1 → http://localhost:10848 — see INSTALL.md.

Tauri desktop installer (~15 MB, no Python required): just build-native — see docs/DEVELOPMENT.md.

Requirements

  • Claude Desktop (or any MCP client for manual config)
  • Blender 3.0+ — installed separately, never bundled; override with BLENDER_EXECUTABLE
  • LLM (optional) — Ollama, LM Studio, or cloud API for script generation; see INSTALL.md
  • OS: Windows, macOS, Linux
  • Python 3.12+ — only for Options C/D (clone-from-source)

License

MIT — FlowEngineer sandraschi. Free for personal and commercial use.

Ver o original no GitHub

Bom para

Relacionados