blender-mcp
The blender-mcp server provides AI-powered natural language control over Blender, enabling comprehensive 3D creation, animation, rendering, and asset management through 80+ specialized MCP tools and agentic workflows.
AI-Powered Creation & Automation
Control Blender via natural language prompts; LLMs generate and execute Blender Python scripts
Multi-step autonomous workflows, batch operations, async job queue, and vision-based refinement loops
Generate 3D meshes from text/images via Tripo, Rodin, and Hunyuan3D backends
3D Modeling & Editing
Create primitives and complex objects (furniture, rooms, etc.); extrude, bevel, subdivide, merge, join/separate
Modifiers: subdivision surface, bevel, mirror, solidify, array, boolean, decimate, displace, wave
Sculpting: dynamic topology, voxel remesh, symmetrize; UV unwrapping (smart project, cube/sphere/cylinder projection)
Procedural modeling via Geometry Nodes; Grease Pencil for 2D drawing and animation
Materials, Textures & Shaders
Create PBR materials (metal, glass, fabric, wood, ceramic) with full shader node graph control
Procedural textures (noise, voronoi, musgrave, checker, brick, gradient)
Texture baking (toon/MToon to PBR), material atlasing for VR optimization
Animation & Rigging
Keyframe animation (location, rotation, scale), shape keys, actions, NLA tracks
Armature creation, IK setup, biped rigs, bone constraints, action baking
VRM facial expressions, visemes, blink animations
Lighting, Camera & Rendering
Create sun/point/spot/area lights, HDRI environments, three-point lighting setups
Render single frames, animation sequences, turntables, and multi-angle shots with Cycles/EEVEE
Compositor post-processing: bloom, SSAO, DOF, motion blur, glow/glare
Viewport screenshots for agent vision feedback
Video Editing (VSE)
Add and manage movie, audio, image, scene, text, and effect strips
Cut, trim, move, apply transitions (CROSS, WIPE, GLOW, GAUSSIAN_BLUR), and export to MP4/H264
Import & Export
Import: FBX, OBJ, GLTF/GLB, STL, PLY, CAD (STEP/IGES via Mayo/FreeCAD), and more
Export: GLB, GLTF, FBX, OBJ, STL, USD, VRM; platform presets for VRChat, Unity, Resonite, Unreal
Download files from URLs and import directly; batch image resize/convert
VR & Avatar Pipeline
VRM metadata management (spring bones, first-person offsets, look-at settings)
Platform validation (polycount, bones, materials, transforms) for VRChat, Resonite, Unity
Gaussian splatting: import, crop/clean, generate collision meshes, export for Resonite
Asset & Library Management
Search and import from Poly Haven (HDRIs, textures, models) and Sketchfab
Manage a local object repository; install, enable, and remove Blender add-ons
Scene & Session Management
Manage scenes, collections, view layers, cameras, object transforms, and selections
Run headless or connect to a live Blender GUI session for real-time feedback
System & Utilities
Server status, logs, health checks, config management (LLM provider, theme, settings)
Blender Python API documentation lookup; local LLM model management (Ollama)
Cross-MCP asset handoff for downstream tools (Godot, Unity, FreeCAD, Tahoma2D)
Controls Blender 3D creation suite, enabling natural language generation of 3D scenes, objects, animations, and renders.
Supports import and export of glTF 3D model files for cross-platform compatibility.
Exports 3D assets and scenes to Unity for game development and VR applications.
Exports 3D assets and avatars to VRChat for virtual reality social platforms.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@blender-mcpcreate a glass sphere with a metal base"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Mode | Host app | When |
Headless (default) |
| Batch export, CI, agents without a display; VSE, geonodes, most mesh ops |
Live GUI (optional) | Blender + bridge addon | Watch the agent build; viewport screenshots; sculpt with live feedback |
Per-tool override |
| Batch 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_sessionstart + enable the bridge addon only if you want the viewport to update live while the agent works. See INSTALL.md.
Related MCP server: BlenderMCP
Hands-in / Hands-out
Direction | Artifacts | Notes |
Hands-in | Natural-language scene prompts | Agent instructions; |
Hands-in |
| Webapp upload or tool params |
Hands-in | Rodin / Tripo / Hunyuan mesh URLs |
|
Hands-in | Inline |
|
Hands-out |
|
|
Hands-out |
| Export + validation pipeline — headless |
Hands-out |
| After agent edit session — headless or live bridge |
Hands-out | Viewport PNG, MP4 (VSE), Gaussian splats |
|
Fleet pipelines (downstream)
Downstream MCP | Takes from blender-mcp |
| |
| |
Rendered image sequences / GP output | |
| |
|
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,
.mcpbpackaging, Prometheus metrics, optional Docker
Quick Install
Download
blender-mcp-*.mcpbfrom ReleasesDrag 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
Doc | Contents |
All install methods, prerequisites, bridge setup | |
Env vars, Claude Desktop | |
Capabilities and tool catalog | |
Contributing, | |
Common errors and fixes | |
System design | |
Planned improvements | |
Prometheus / Grafana / Loki | |
Optional 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_EXECUTABLELLM (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.
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sandraschi/blender-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server