← Back to directory
B

Blender Open MCP

Community
Control Blender 3D with natural language via local AI models
GitHub source repository ↗
★ 111 Stars Category · Dev Tools Popular Source revision d7207037412d
40FMRS · D
Reliability
6/20
Security and permissions
3/20
Maintenance
6/20
Documentation
13/20
Setup experience
12/20

This server provides a practical MCP integration to control Blender via natural language through local Ollama models, suitable for developers and 3D artists. Its architecture is clear and tools are rich, including scene operations, materials, rendering, and AI assistance. However, executing arbitrary code and deleting objects pose security risks, requiring caution. It is non-official, depends on local models, and is not suitable for users needing cloud AI or low security risk.

Read the FMRS scoring method →

Built on the Model Context Protocol (MCP), connecting Claude, Cursor, or any MCP client to Blender through a local Ollama LLM. Architecture uses FastMCP server, Blender add-on, and Ollama.

Tools

blender_get_scene_info
Full scene summary: objects, camera, render settings
blender_get_object_info
Detailed object info: transforms, materials, mesh stats
blender_create_object
Add a primitive mesh (CUBE, SPHERE, CYLINDER, ...)
blender_modify_object
Change location, rotation, scale, visibility
blender_delete_object
Remove an object from the scene
blender_set_material
Create and assign a Principled BSDF material
blender_render_image
Render current scene to a file
blender_execute_code
Run arbitrary Python/bpy code in Blender
blender_get_polyhaven_categories
List PolyHaven asset categories
blender_search_polyhaven_assets
Search PolyHaven library with pagination
blender_download_polyhaven_asset
Download & import a PolyHaven asset
blender_set_texture
Apply a downloaded PolyHaven texture to an object
blender_ai_prompt
Send a natural language prompt to Ollama
blender_get_ollama_models
List available local Ollama models
blender_set_ollama_model
Switch the active Ollama model
blender_set_ollama_url
Update the Ollama server URL

Setup

  1. Install dependencies: Blender 3.0+, Python 3.10+, Ollama, uv.
  2. Clone repo and set up virtual env: uv venv, activate, uv pip install -e ..
  3. Install Blender add-on: Edit → Preferences → Add-ons → Install, select addon.py, enable "Blender MCP", start MCP server in N-sidebar (default port 9876).
  4. Pull an Ollama model: ollama pull ollama run llama3.2.
  5. Start Ollama server.
  6. Start MCP server: blender-mcp, or with custom options like --transport stdio.
claude_desktop_config.json
{
  "mcpServers": {
    "blender-open-mcp": {
      "command": "blender-mcp",
      "args": ["--transport", "stdio"]
    }
  }
}

Fit and risk

Best for

  • 3D artists who want to control Blender with local AI models
  • Developers who need to automate 3D workflows
  • Users integrating with Claude Desktop or Cursor for AI-assisted modeling

Not for

  • Users without local Ollama or ability to run local LLMs
  • Users needing cloud AI services (since it uses local models)
  • Users unfamiliar with Blender add-on installation
  • Users requiring official support (non-official project)

Required permissions

  • Can read and modify Blender scene (objects, materials, transforms)
  • Can execute arbitrary Python/bpy code via blender_execute_code
  • Can delete objects via blender_delete_object
  • Can render images to files
  • Can access internet to download PolyHaven assets
  • Can access local models via Ollama
  • Requires network ports (8000, 9876, 11434)

Risks and side effects

  • Executing arbitrary code may corrupt scenes or systems if given malicious prompts
  • Deleting objects is irreversible and may lose work
  • PolyHaven downloads require internet and may fail
  • Local LLM may generate inaccurate code; review before execution
  • Non-official project may have bugs or security vulnerabilities

Troubleshooting

  1. Cannot connect to Blender add-on: start MCP server in Blender sidebar
  2. Cannot connect to Ollama: run `ollama serve`
  3. Object not found: check exact name via `blender_get_scene_info`
  4. Render fails: ensure output directory exists and is writable
  5. PolyHaven download fails: check internet connection; try lower resolution

Use cases

Create and modify 3D objects in Blender via natural language commands
Use AI assistant to generate and execute bpy code
Download and apply textures from PolyHaven
Automate scene rendering
Get scene and object information for AI analysis

Supported clients

Claude DesktopFull support
CursorFull support