MCP for Blender Capabilities: What You Can Build

MCP for Blender gives your AI client a toolkit of actions in Blender, from reading scene state to downloading production-ready assets.

Capability Overview

Scene Generation

Build complete scenes from a prompt: layout, props, lighting, HDRI environments, and cameras.

Asset Generation

Generate custom 3D models from text or reference images with Hyper3D Rodin and Hunyuan3D.

Animation

Keyframe objects, cameras, and lights, and set up turntables, camera moves, and timeline ranges.

Rigging

Add armatures, bones, constraints, and weight parenting so models are ready to pose and animate.

Scene Inspection

Read the full scene graph, object lists, transforms, and collections in real time.

Object Manipulation

Create, move, rotate, scale, rename, and delete objects using natural language prompts.

Material Control

Assign and configure materials, textures, and shaders on any object in the scene.

Code Execution

Run arbitrary Blender Python (bpy) for operations not covered by built-in tools.

Asset Integration

Search and download HDRIs, textures, and 3D models from Poly Haven, Sketchfab, Poly Pizza, Hyper3D, and Hunyuan3D.

Viewport Screenshots

Capture the current 3D viewport and return it to the AI client for visual feedback.

Use Cases

See how these capabilities come together for specific kinds of work.

Gaming

Game-ready assets, low-poly environments, and level prototypes.

Architecture

Architectural scenes with PBR materials, lighting, and furniture.

Scientific Visualization

Molecular models, geographic representations, and data-driven scenes.

Robotics Simulation

Simulation environments, obstacle courses, and sensor test scenes.

Filmmaking & VFX

Cinematic scenes, camera setups, hero assets, and environment lighting.

Asset Creation

Production-ready assets generated from text prompts or reference images.

Scene Generation

Complete scenes that combine library assets and AI generation in one workflow.

What People Have Made

These were built by people describing what they wanted to an LLM connected to Blender through MCP for Blender.

GPT-6 Astra & Opus 5.5 + Unreal + Blender This is my last post about this project. My 16GB MacBook is starting to struggle with Unreal, so I’m thinking about going back to Godot and making a different game instead. I’ll leave a short summary below

@seftsaint

dude GPT-6 Astra is some kind of turbo-AGI machine god for 3D games. It one-shot this in 45 minutes for hardly a couple % of my quota. I figured out how to get great graphics out of it. The trick is image gen. I'll share the process below.

@anshuc

I asked Astra to make a photorealistic bat in Blender, and it just kept going until I ran out of tokens. This is AGI.

@aollivier82

just asked gpt-5.6 sol in cursor to set up blender mcp and make me a realistic floating macbook, then render the whole thing. never opened blender once in my life before today.

@prasenx

computer use is super cool in so many things but blender mcp seems better so far, these results are one shots

@developedbyed

BlenderMCPを導入して簡易プレビズを作り、それを参照動画としてSeedance2に渡すワークフローを試しました。上段がBlenderで作ったラフなプレビズ。下段がそれを参照させてSeedance2で生成したショットです。私はBlender初心者（なんと本日初めて触りました。）ですが、Claude + Blender

@wtry1102

See everything people have made →

Full Tool Reference

Tool	Category	What It Does
`get_scene_info`	Scene	Returns the full scene graph, objects, and collections.
`get_object_info`	Scene	Returns detailed data for a specific object by name.
`get_viewport_screenshot`	Viewport	Captures the current 3D viewport as an image.
`execute_blender_code`	Code	Runs arbitrary Python in Blender and returns the result.
`get_polyhaven_status`	Asset	Checks whether Poly Haven integration is enabled and reachable.
`search_polyhaven_assets`	Asset	Searches Poly Haven for HDRIs, textures, or models.
`download_polyhaven_asset`	Asset	Downloads and imports a Poly Haven asset into the scene.
`set_texture`	Material	Applies a texture or material to the selected object.
`search_sketchfab_models`	Asset	Searches Sketchfab for downloadable 3D models.
`download_sketchfab_model`	Asset	Downloads and imports a Sketchfab model into the scene.
`search_polypizza_models`	Asset	Searches Poly Pizza for low-poly 3D models.
`download_polypizza_model`	Asset	Downloads and imports a Poly Pizza model into the scene.
`generate_hyper3d_model_via_text`	AI	Generates a 3D model from a text prompt using Hyper3D Rodin.
`generate_hyper3d_model_via_images`	AI	Generates a 3D model from one or more images using Hyper3D Rodin.
`poll_rodin_job_status`	AI	Checks the generation status of a Hyper3D Rodin job.
`import_generated_asset`	AI	Imports a completed Hyper3D Rodin model into Blender.
`generate_hunyuan3d_model`	AI	Generates a 3D model from text or image using Hunyuan3D.
`poll_hunyuan_job_status`	AI	Checks the generation status of a Hunyuan3D job.
`import_generated_asset_hunyuan`	AI	Imports a completed Hunyuan3D model into Blender.

Limitations

Complex operations may need to be broken into smaller steps. The AI client works best with incremental, explicit instructions rather than single large prompts that try to do everything at once.

Blender must be running with a GUI. Headless mode (blender -b) is not supported unless you use xvfb-run -a blender to provide a virtual display.

Only one MCP server instance can connect to Blender at a time. Do not run both Cursor and Claude Desktop against the same Blender session simultaneously.