by ahujasid
Enables Claude AI to control Blender for prompt‑assisted 3D modeling, scene creation, and manipulation via a socket‑based Model Context Protocol server.
BlenderMCP provides a two‑way communication channel between Claude (or other AI assistants) and Blender. By running a socket server inside Blender and a Model Context Protocol (MCP) server on the host, the AI can send JSON commands to create, modify, or delete objects, apply materials, inspect the scene, and even execute arbitrary Python code directly inside Blender.
uv
package manager (install via Homebrew on macOS or PowerShell script on Windows).claude_desktop_config.json
under mcpServers.blender
:{
"command": "uvx",
"args": ["blender-mcp"]
}
.cursor/mcp.json
with the same structure, or add a global server via the UI.addon.py
from the repository.addon.py
, and enable it.uvx blender-mcp
in a terminal (only one instance – either Claude or Cursor).Q: Can I run the server on both Claude and Cursor simultaneously? A: No. Only one MCP server instance should be active at a time; running two will cause port conflicts.
Q: Do I need an internet connection for Poly Haven or Hyper3D? A: Yes. Poly Haven assets are downloaded on demand, and Hyper3D requires an API key (free trial or personal key).
Q: Is executing arbitrary Python code safe?
A: The execute_blender_code
tool can run any Python, which is powerful but risky. Always save your work before using it and limit usage to trusted environments.
Q: What operating systems are supported? A: BlenderMCP works on macOS, Linux, and Windows as long as Blender 3.0+ and Python 3.10+ are installed.
Q: How do I troubleshoot connection problems?
A: Ensure the addon is enabled, the MCP server is running (uvx blender-mcp
), and the correct config snippet is placed in the AI client. Restart both Blender and the AI client if issues persist.
BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
We have no official website. Any website you see online is unofficial and has no affiliation with this project. Use them at your own risk.
Give feedback, get inspired, and build on top of the MCP: Discord
Available for MacOS, Linux, & Windows
Other supporters:
All supporters:
The system consists of two main components:
addon.py
): A Blender addon that creates a socket server within Blender to receive and execute commandssrc/blender_mcp/server.py
): A Python server that implements the Model Context Protocol and connects to the Blender addonIf you're on Mac, please install uv as
brew install uv
On Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
and then
set Path=C:\Users\nntra\.local\bin;%Path%
Otherwise installation instructions are on their website: Install uv
⚠️ Do not proceed before installing UV
Watch the setup instruction video (Assuming you have already installed uv)
Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:
{
"mcpServers": {
"blender": {
"command": "uvx",
"args": [
"blender-mcp"
]
}
}
}
For Mac users, go to Settings > MCP and paste the following
.cursor/mcp.json
in the root of the project and paste{
"mcpServers": {
"blender": {
"command": "uvx",
"args": [
"blender-mcp"
]
}
}
}
For Windows users, go to Settings > MCP > Add Server, add a new server with the following settings:
{
"mcpServers": {
"blender": {
"command": "cmd",
"args": [
"/c",
"uvx",
"blender-mcp"
]
}
}
}
⚠️ Only run one instance of the MCP server (either on Cursor or Claude Desktop), not both
addon.py
file from this repoaddon.py
fileOnce the config file has been set on Claude, and the addon is running on Blender, you will see a hammer icon with tools for the Blender MCP.
Here are some examples of what you can ask Claude to do:
Hyper3D's free trial key allows you to generate a limited number of models per day. If the daily limit is reached, you can wait for the next day's reset or obtain your own key from hyper3d.ai and fal.ai.
The system uses a simple JSON-based protocol over TCP sockets:
type
and optional params
status
and result
or message
execute_blender_code
tool allows running arbitrary Python code in Blender, which can be powerful but potentially dangerous. Use with caution in production environments. ALWAYS save your work before using it.Contributions are welcome! Please feel free to submit a Pull Request.
This is a third-party integration and not made by Blender. Made by Siddharth
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by Skyvern-AI
Automates browser‑based workflows by leveraging large language models and computer‑vision techniques, turning natural‑language prompts into fully functional web interactions without writing custom scripts.
by PipedreamHQ
Connect APIs quickly with a free, hosted integration platform that enables event‑driven automations across 1,000+ services and supports custom code in Node.js, Python, Go, or Bash.
by elie222
Organizes email inbox, drafts replies in the user's tone, tracks follow‑ups, and provides analytics to achieve inbox zero quickly.
by grab
Enables Cursor AI to read and programmatically modify Figma designs through a Model Context Protocol integration.
by ahujasid
Enables Claude AI to control Ableton Live in real time, allowing AI‑driven creation, editing, and playback of tracks, clips, instruments, and effects through a socket‑based server.
by leonardsellem
Provides tools and resources to enable AI assistants to manage and execute n8n workflows via natural language commands.
by GongRzhe
Provides a Model Context Protocol server that enables AI assistants to send, read, search, and organize Gmail messages, supporting attachments, label and filter management, and automatic OAuth2 authentication.
by mario-andreschak
A unified platform that manages AI models, MCP servers, and complex workflows, offering secure key storage, visual flow building, and an interactive chat UI.
by tevonsb
Provides a Model Context Protocol server that exposes Home Assistant functionality through a comprehensive REST and SSE API, enabling natural‑language control of smart‑home devices.