Houdini MCP Server
Enables natural language control of SideFX Houdini for tasks including node management, parameter editing, and geometry inspection. It leverages RPYC to execute Python scripts and manage scene data through an MCP-compatible interface.
README
Houdini MCP Server
Control SideFX Houdini from AI assistants via the Model Context Protocol.
35 tools for node creation, parameter editing, geometry inspection, scene management, and arbitrary Python execution — all driven by natural language through Claude or any MCP-compatible client.
Features
- Node operations — create, delete, rename, connect, layout, cook, find nodes
- Parameter control — get/set values, list parameters, set expressions
- Geometry inspection — read points, primitives, bounding boxes, export
.geo - Scene management — new/open/save scenes, scene info
- Transform tools — get/set object transforms
- Code execution — run arbitrary Python or HScript inside Houdini
- Built-in documentation — 11 comprehensive HOM reference docs + 5 index files, searchable via MCP tools
Prerequisites
Setup
1. Start RPYC server in Houdini
Open Houdini's Python Shell (Windows > Python Shell) and run:
import hrpyc
hrpyc.start_server(port=18811)
Or use the provided helper script:
exec(open("/path/to/houdini-mcp/houdini_setup.py").read())
2. Configure your MCP client
Add to your MCP client configuration (e.g., .mcp.json for Claude Code):
{
"mcpServers": {
"houdini": {
"command": "uv",
"args": ["--directory", "/path/to/houdini-mcp", "run", "server.py"]
}
}
}
Replace /path/to/houdini-mcp with the actual path to this repo.
3. Connect
Call the houdini_connect tool first. Then use any of the 35 available tools.
Claude Code Skill (Optional)
The claude-skill/ directory contains a Houdini Python reference skill for Claude Code. To use it:
- Copy
claude-skill/houdini-python.mdto your project's.claude/commands/directory - The skill provides HOM API reference, SOP/DOP/VOP node guides, and scripting patterns
- Invoke with
/houdini-pythonin Claude Code
Tools
| Category | Tools |
|---|---|
| Connection | houdini_connect, houdini_disconnect |
| Scene | houdini_scene_new, houdini_scene_open, houdini_scene_save, houdini_scene_info |
| Nodes | houdini_node_create, houdini_node_delete, houdini_node_rename, houdini_node_connect, houdini_node_cook, houdini_node_info, houdini_node_children, houdini_node_find, houdini_node_layout, houdini_node_set_flags |
| Parameters | houdini_parm_get, houdini_parm_set, houdini_parm_list, houdini_parm_set_expression |
| Geometry | houdini_geo_info, houdini_geo_read_points, houdini_geo_read_prims, houdini_geo_bbox, houdini_geo_export |
| Transforms | houdini_transform_get, houdini_transform_set |
| Execution | houdini_execute, houdini_hscript |
| Frame | houdini_set_frame |
How it works
┌──────────────┐ MCP (stdio) ┌──────────────┐ RPYC (TCP) ┌──────────────┐
│ AI Client │ ◄─────────────────► │ MCP Server │ ◄────────────────► │ Houdini │
│ (Claude etc) │ │ (server.py) │ │ (port 18811)│
└──────────────┘ └──────────────┘ └──────────────┘
The MCP server translates tool calls into RPYC remote procedure calls to Houdini's Python interpreter. Houdini runs an RPYC server (via hrpyc) that exposes the full hou module.
License
MIT
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。