Skip to main content
Glama

Blender MCP Server

by llm-use

Blender MCP Server

Production-ready Model Context Protocol (MCP) server for complete Blender control via API

This addon transforms Blender into an MCP server, exposing 50+ powerful tools that can be orchestrated by AI agents through HTTP endpoints. Perfect for AI-driven 3D workflows, automation, and creative experimentation.

✨ Features

  • šŸš€ 50+ Production-Ready Tools - Complete control over Blender's features:

    • Object creation, manipulation, and transformation

    • Material and shader system management

    • Animation and keyframe control

    • Camera and lighting setup

    • Modifiers and constraints

    • Physics simulations (rigid body, cloth, fluid)

    • Geometry nodes and procedural generation

    • File import/export operations

    • Scene optimization and batch operations

  • šŸ”’ Thread-Safe Execution - Enterprise-grade queue system for safe concurrent operations

  • šŸ“¦ Auto-Install Dependencies - Automatically installs required packages on first run

  • šŸŽ® Simple UI Panel - Start/stop server with one click from Blender's N-panel

  • šŸ“Š Real-time Monitoring - Track operations, statistics, and server status

  • šŸ”§ Production-Ready - Comprehensive error handling, logging, and caching

šŸš€ Quick Start

Installation

  1. Download blender_mcp.py

  2. Open Blender

  3. Go to Edit → Preferences → Add-ons

  4. Click the dropdown arrow (āŒ„) next to the search bar

  5. Select Install from Disk...

  6. Choose the downloaded blender_mcp.py file

  7. Enable the addon by checking the box next to "MCP Complete Server for Blender"

Starting the Server

  1. Press N in the 3D Viewport to open the sidebar

  2. Navigate to the MCP Server tab

  3. Click Start Server

  4. Server will start on http://localhost:8000

The addon will automatically install required dependencies on first run (FastAPI, Uvicorn, Pydantic, etc.).

šŸ¤– Using with PolyMCP

This MCP server is designed to work seamlessly with PolyMCP - a powerful framework for orchestrating MCP servers with AI agents.

Example: AI-Controlled Blender

#!/usr/bin/env python3 import asyncio from polymcp.polyagent import UnifiedPolyAgent, OllamaProvider async def main(): # Initialize your LLM provider llm = OllamaProvider(model="gpt-oss:20b", temperature=0.1) # Connect to Blender MCP server agent = UnifiedPolyAgent( llm_provider=llm, mcp_servers=["http://localhost:8000/mcp"], verbose=True ) async with agent: print("āœ… Blender MCP Server connected!\n") # Chat with your AI to control Blender while True: user_input = input("\nšŸŽØ You: ") if user_input.lower() in ['exit', 'quit']: break result = await agent.run_async(user_input, max_steps=5) print(f"\nšŸ¤– Blender: {result}") if __name__ == "__main__": asyncio.run(main())

Example Commands

Once connected, you can ask the AI agent to:

  • "Create a cube at position (0, 0, 0) with size 2"

  • "Add a red metallic material to the selected object"

  • "Create a camera looking at the origin"

  • "Set up a simple lighting scene with 3 lights"

  • "Add a fluid simulation to the cube"

  • "Export the scene as an FBX file"

  • "Create an animation rotating the object 360 degrees over 100 frames"

That's it! PolyMCP handles all the complexity of:

  • Tool discovery and selection

  • Multi-step task planning

  • Error handling and retries

  • State management across operations

This makes it incredibly simple to build AI-powered Blender automation tools!

šŸ“” API Endpoints

Once the server is running, you can access:

  • API Documentation: http://localhost:8000/docs

  • List All Tools: http://localhost:8000/mcp/list_tools

  • Invoke Tool: POST http://localhost:8000/mcp/invoke/{tool_name}

šŸ› ļø Available Tool Categories

  • Object Operations: Create, delete, duplicate, select objects

  • Transformations: Move, rotate, scale, apply transforms

  • Materials & Shading: Create materials, add textures, setup shader nodes

  • Modeling: Add modifiers, boolean operations, mesh editing

  • Animation: Keyframes, timeline control, NLA editor

  • Camera & Lighting: Camera setup, light creation, HDRI environments

  • Rendering: Render settings, output configuration, rendering

  • Physics: Rigid body, cloth, fluid simulations

  • Geometry Nodes: Procedural generation, node tree creation

  • File Operations: Import/export various formats (FBX, OBJ, USD, etc.)

  • Scene Management: Scene info, cleanup, optimization

  • Batch Operations: Multi-object creation and transformation

  • Advanced: Particle systems, force fields, grease pencil

šŸ”§ Configuration

You can customize the server by editing the Config class in blender_mcp.py:

class Config: HOST = "0.0.0.0" # Server host PORT = 8000 # Server port AUTO_INSTALL_PACKAGES = True # Auto-install dependencies THREAD_SAFE_OPERATIONS = True # Enable thread-safe execution ENABLE_CACHING = True # Enable result caching

šŸ“‹ Requirements

The addon automatically installs these dependencies:

  • FastAPI

  • Uvicorn

  • Pydantic

  • docstring-parser

  • NumPy

  • PolyMCP

Blender Version: 3.0.0 or higher

šŸ› Troubleshooting

Server won't start?

  • Check Blender's System Console for error messages (Window → Toggle System Console)

  • Ensure port 8000 is not already in use

  • Try restarting Blender after installation

Dependencies not installing?

  • Manually install packages using Blender's Python:

    /path/to/blender/python -m pip install fastapi uvicorn pydantic docstring-parser numpy

Can't find MCP Server panel?

  • Press N in the 3D Viewport

  • Look for "MCP Server" tab in the sidebar

  • Make sure the addon is enabled in Preferences

šŸ¤ Contributing

Contributions are welcome! This project demonstrates how simple it is to create powerful MCP servers for PolyMCP.

šŸ“ License

MIT License - See LICENSE file for details

šŸ”— Related Projects

  • PolyMCP - Simple and efficient way to interact with MCP servers using custom agents

  • Model Context Protocol - Open protocol for tool integration with LLMs

šŸ’” Why This Project?

This MCP server was created to demonstrate how incredibly simple PolyMCP makes it to build AI-powered tools. With just a few lines of code, you can:

  1. Expose complex Blender functionality as MCP tools

  2. Let AI agents discover and orchestrate these tools

  3. Build natural language interfaces for 3D creation

No complex prompting, no manual tool selection, no state management - PolyMCP handles it all!


Designed for

Star ⭐ this repo if you find it useful!

-
security - not tested
A
license - permissive license
-
quality - not tested

local-only server

The server can only run on the client's local machine because it depends on local resources.

Transforms Blender into an MCP server with 50+ tools for AI-driven 3D workflows, enabling complete control over objects, materials, animations, physics simulations, and rendering through natural language commands.

  1. ✨ Features
    1. šŸš€ Quick Start
      1. Installation
      2. Starting the Server
    2. šŸ¤– Using with PolyMCP
      1. Example: AI-Controlled Blender
      2. Example Commands
    3. šŸ“” API Endpoints
      1. šŸ› ļø Available Tool Categories
        1. šŸ”§ Configuration
          1. šŸ“‹ Requirements
            1. šŸ› Troubleshooting
              1. šŸ¤ Contributing
                1. šŸ“ License
                  1. šŸ”— Related Projects
                    1. šŸ’” Why This Project?

                      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/llm-use/Blender-MCP-Server'

                      If you have feedback or need assistance with the MCP directory API, please join our Discord server