blender-ai-mcp
Connects MCP-compatible clients to a live Blender scene for AI-assisted 3D workflows, enabling inspection and controlled operations on objects, materials, cameras, lights, render settings, animation, UVs, Geometry Nodes, imports, exports, and Python execution.
README
blender-ai-mcp
blender-ai-mcp is a local Model Context Protocol server plus Blender addon bridge for AI-assisted 3D workflows.
It lets an MCP client inspect the live Blender scene and perform controlled operations on objects, materials, cameras, lights, render settings, animation, UVs, Geometry Nodes, imports, exports, and Python execution.
What Is Included
server/: Python MCP server and tool registry.blender_addon/: Blender addon that receives commands from the local bridge.blender_ai_mcp/: package entry points for MCP clients.docs/: setup, tool reference, and AI usage notes.
Requirements
- Blender 3.6 LTS or newer.
- Python 3.10 or newer.
- Claude Desktop or another MCP-compatible client.
Quick Start
-
Create and activate a virtual environment.
python -m venv .venv .\.venv\Scripts\Activate.ps1 pip install -r requirements.txt -
Install the addon from
blender_addon/.In Blender, open
Edit > Preferences > Add-ons > Install..., selectblender_addon/__init__.py, and enable AI MCP Bridge. -
Start the addon server in Blender.
In the 3D Viewport sidebar, open the AI MCP panel, confirm port
9876, and click Start Server. -
Configure your MCP client using
mcp_config_example.json. -
Restart the client and confirm the
blenderserver is available.
MCP Config
Example:
{
"mcpServers": {
"blender": {
"command": "python",
"args": ["-m", "blender_ai_mcp.server.main"],
"env": {
"BLENDER_MCP_PORT": "9876",
"BLENDER_MCP_HOST": "localhost"
}
}
}
}
If you use a project virtual environment, set command to that environment's Python executable.
Typical Workflow
- Inspect the live scene with
get_scene_infoandlist_objects. - Create or reuse the target object.
- Fix the origin if
locationandbounding_box_centerdo not match. - Position, align, and duplicate objects using the layout tools.
- Apply materials and modifiers.
- Validate overlaps, scale, and scene quality.
- Render a viewport preview before reporting the task done.
Validation
Run the test suite after code changes:
pytest
Useful checks:
ruff check .uv run --extra dev pytest tests
Documentation
Safety
The execute_python and expression-evaluation tools are for trusted local workflows only. Do not expose the Blender addon socket to a public network.
License
MIT. See LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。