maya_mcp
A Model Context Protocol server that enables AI assistants to interact with active Autodesk Maya sessions using the maya.cmds API. It allows users to manage scene objects, control selections, and perform common 3D operations through natural language.
README
maya_mcp
FastMCP-based Model Context Protocol (MCP) server for Autodesk Maya. This server enables AI assistants and other MCP clients to interact with an active Maya session, control scene objects, and perform common 3D operations.
Features
- FastMCP Framework: Built on FastMCP for easy tool, resource, and prompt registration
- Maya Integration: Communicate with active Maya sessions via maya.cmds API
- Flexible Deployment: Can be started from within Maya or from a mayapy process
- Extensible: Easy to add new tools, resources, and prompts
Installation
Development Installation
# Using pip
pip install -e .
# Using uv
uv pip install -e .
Requirements
- Python 3.10+ (3.11+ recommended)
- FastMCP >= 2.0.0
- Autodesk Maya (for running the server with Maya)
Usage
Starting the Server from Maya
- Open Maya
- In the Maya Script Editor, run:
import sys
sys.path.insert(0, r'F:\git\maya_mcp\src\py') # Adjust path as needed
import maya_mcp
maya_mcp.__main__.main()
Starting the Server from mayapy
# Using mayapy directly
mayapy -m maya_mcp
# Or if installed as a package
mayapy -c "from maya_mcp import mcp; mcp.run()"
Starting as a Standalone Script
If installed via pip/uv:
maya-mcp
Note: The server will warn if Maya is not available, but some tools may not work.
Available Tools
Server Status
get_server_status()- Get the status of the Maya MCP server
Scene Operations
get_selection()- Get currently selected objectsselect_objects(names)- Select objects by nameclear_selection()- Clear the current selection
More tools will be added as the project develops.
Project Structure
maya_mcp/
├── src/
│ └── py/
│ └── maya_mcp/
│ ├── __init__.py # Main FastMCP server setup
│ ├── __main__.py # Entry point for running the server
│ ├── server.py # Core server setup and status tools
│ ├── tools/ # Tool implementations
│ │ ├── __init__.py
│ │ └── scene.py # Scene manipulation tools
│ ├── resources/ # Resource implementations
│ │ └── __init__.py
│ └── prompts/ # Prompt templates
│ └── __init__.py
├── tests/ # Unit tests (to be added)
├── pyproject.toml # Project configuration
├── README.md # This file
└── AGENTS.md # AI agent guidance
Development
See AGENTS.md for detailed guidance on developing and extending the Maya MCP server.
Running Tests
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest tests/
# With coverage
pytest tests/ --cov=src/py/maya_mcp --cov-report=term-missing
License
Apache License 2.0
Author
Ben Deda
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。