Blender MCP Server
Enables AI agents to fully control Blender through 50+ tools for 3D modeling, animation, materials, and scene management via HTTP endpoints.
README
Blender MCP Server
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
-
š 50+ 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
-
š Thread-Safe Execution - Enterprise-grade queue system for safe concurrent operations
-
š¦ Auto-Install Dependencies - Automatically installs required packages on first run
-
š® Simple UI Panel - Start/stop server with one click from Blender's N-panel
-
š Real-time Monitoring - Track operations, statistics, and server status
-
š§ Production-Ready - Comprehensive error handling, logging, and caching
š Quick Start
Installation
- Download
blender_mcp.py - Open Blender
- Go to Edit ā Preferences ā Add-ons
- Click the dropdown arrow (ā) next to the search bar
- Select Install from Disk...
- Choose the downloaded
blender_mcp.pyfile - Enable the addon by checking the box next to "MCP Complete Server for Blender"
Starting the Server
- Press N in the 3D Viewport to open the sidebar
- Navigate to the MCP Server tab
- Click Start Server
- Server will start on
http://localhost:8000
The addon will automatically install required dependencies on first run (FastAPI, Uvicorn, Pydantic, etc.).
š¤ 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:120b-cloud", 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("ā
Blender MCP Server connected!\n")
# Chat with your AI to control Blender
while True:
user_input = input("\nšØ You: ")
if user_input.lower() in ['exit', 'quit']:
break
result = await agent.run_async(user_input, max_steps=5)
print(f"\nš¤ 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!
š” 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}
š§ 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
š Requirements
The addon automatically installs these dependencies:
- FastAPI
- Uvicorn
- Pydantic
- docstring-parser
- NumPy
- PolyMCP
Blender Version: 3.0.0 or higher
š Troubleshooting
Server won't start?
- Check Blender's System Console for error messages (Window ā 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.