Allows AI agents to control Blender 3D scenes, providing tools for scene inspection, object creation and transforms, materials and textures, modifiers, timeline control, rendering, viewport screenshots, and asset imports.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Blender MCP Create a cube and assign a red glossy material to it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol bridge that lets MiniMax Code (and any MCP client) drive Blender 5.2 LTS through natural language. Ships as two artifacts:
Artifact | What it is | Where it lives |
Blender add-on | Python add-on that runs an MCP Streamable-HTTP server inside Blender on a background thread |
|
MiniMax Plugin V1 | Local MiniMax Code plugin that connects to the running Blender MCP server and exposes its tools to the agent |
|
The Blender add-on is the source of truth for Blender-side state. The MiniMax plugin is a thin client that calls the add-on's HTTP endpoint — no Python process is spawned on the MiniMax side, so there's no port-leak or lifecycle mess.
Single install path inside Blender — the MCP server runs in-process
using bpy, so there's no uvx/pipx dance and no socket pair to keep
in sync.
Streamable HTTP on localhost — works with any modern MCP client (MiniMax Code, Claude Desktop, Cursor) and survives Blender restarts.
Hand-rolled MCP server in the add-on — Blender 5.2 LTS bundles Python
3.13 with no external packages by default. A ~300-line MCP server is more
portable than dragging in mcp[cli] and editing sys.path.
MiniMax Plugin V1 with streamable-http capability — the plugin
doesn't spawn anything; it just points at the Blender add-on's endpoint.
Related MCP server: Blender MCP VXAI
blender_addon_mcp/
├── README.md ← you are here
├── LICENSE ← MIT
├── pyproject.toml ← dev tooling for the add-on (ruff, mypy, pytest)
├── .gitignore
├── addon/
│ └── blender_mcp_addon/ ← zips into a Blender-installable .zip
│ ├── __init__.py ← bl_info, register/unregister
│ ├── preferences.py ← AddOnPreferences (port, auth token, autostart)
│ ├── server/
│ │ ├── __init__.py
│ │ ├── mcp_server.py ← MCP protocol (initialize, tools/list, tools/call, ping)
│ │ ├── transport.py ← stdlib http.server, runs on a daemon thread
│ │ └── protocol.py ← JSON-RPC 2.0 + MCP 2025-03-26 types
│ ├── tools/
│ │ ├── __init__.py ← tool registry
│ │ ├── scene.py ← scene_info, frame control
│ │ ├── objects.py ← list, get, create, delete, transform
│ │ ├── materials.py ← create, assign, modify
│ │ ├── modifiers.py ← add, set params, remove
│ │ ├── render.py ← render_image, screenshot_viewport
│ │ └── code.py ← execute_python (with confirmation)
│ └── utils/
│ ├── __init__.py
│ ├── bpy_helpers.py ← bpy → JSON serialization
│ └── safe_eval.py ← ast-validated code execution
├── connector/ ← MiniMax Plugin V1 source
│ ├── .minimax-plugin/
│ │ └── plugin.json
│ ├── servers/
│ │ └── blender.mcp.json ← streamable-http → http://127.0.0.1:8765/mcp
│ ├── icon.png ← category icon (Design / 3D)
│ └── README.md
├── scripts/
│ ├── install_addon.ps1 ← zip and install into Blender
│ └── install_connector.ps1 ← copy connector into ~/.minimax/plugins/
├── examples/
│ ├── basic_scene.md
│ ├── material_setup.md
│ └── render_workflow.md
└── docs/
├── architecture.md
├── blender_5_2_notes.md
└── tools_reference.md# 1. Clone the repository
git clone https://github.com/tattooinmtl/Minimax_Blender_MCP.git
cd Minimax_Blender_MCP
# 2. Install the Blender add-on
pwsh ./scripts/install_addon.ps1
# 3. Install the MiniMax connector plugin
pwsh ./scripts/install_connector.ps1Open Blender.
Go to Edit → Preferences → Add-ons.
Search for "Blender MCP" and check the box to enable it.
Set the port (default 8765) and click Start Server (or start it from the 3D Viewport sidebar under the Blender MCP tab).
You will see [Blender MCP] Server listening on http://127.0.0.1:8765/mcp in the console.
In a MiniMax Code chat, ask:
Use the blender connector: list the first 5 objects in the current scene.
You should see the agent call tools/list against your running Blender.
Tool | Purpose | Read-only |
| Capability handshake — name, version, protocol, tools list. Call this first. | yes |
| Scene summary (objects, lights, cameras, frame) | yes |
| List scene objects, optional type filter | yes |
| Full object details (location, rotation, scale, modifiers, materials) | yes |
| Create primitive (cube, sphere, plane, cylinder, cone, torus, empty, camera, light) | no |
| Delete an object by name | no |
| Set location/rotation/scale | no |
| Create or assign a material with a Principled BSDF | no |
| Apply an image file to a material input (base_color, roughness, normal, etc.) | no |
| Import GLB/GLTF/FBX/OBJ/STL/PLY/DAE/USD/X3D/ABC | no |
| Add a modifier (subdivision, mirror, solidify, array, bevel) | no |
| Remove a modifier by name | no |
| Read / move the timeline | mixed |
| Render the current frame to a file | no |
| Capture the current viewport | no |
| Run arbitrary | no |
| Health check | yes |
The MiniMax plugin also ships a Skill (blender-mcp-quickstart) that
gives the agent an at-a-glance tool index, safety rules, and common
recipes. Read it before doing non-trivial work.
See docs/tools_reference.md for the full schema
and examples.
# syntax-check the add-on (Blender's Python is at <blender>/python/bin/python.exe)
python -m py_compile addon/blender_mcp_addon/__init__.py
python -m py_compile addon/blender_mcp_addon/server/mcp_server.py
# ...etc
# lint
ruff check addon/
mypy addon/
# test the MCP server in isolation (no bpy required)
pytest addon/tests/ -vMIT. See LICENSE.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Cloud Blender for AI agents: scenes, assets, renders, MP4, STL, GLB — over hosted remote MCP.
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for Producer/Riffusion AI music generation