Houdini MCP Server
Enables AI assistants to control Houdini by executing Python code, querying scene information, and creating nodes via the Model Context Protocol.
README
Houdini MCP Server
Control Houdini from AI assistants via the Model Context Protocol (MCP).
What It Does
Allows MCP-compatible AI tools (like OpenCode, Claude Desktop, etc.) to:
- Execute Python code in Houdini with full
houmodule access - Query scene information (nodes, frames, selection, etc.)
- Create and manipulate nodes programmatically
Install
1. Clone this repo
cd ~/Library/Preferences/houdini/20.5/ # macOS
git clone https://github.com/YOUR_USERNAME/houdini-mcp-server
2. Create Python venv and install dependencies
cd houdini-mcp-server
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
deactivate
3. Install shelf tools (one-liner in Houdini Python Shell)
exec(open('/Users/YOUR_USERNAME/Library/Preferences/houdini/20.5/houdini-mcp-server/install_mcp_shelf.py').read())
4. Configure your AI client
OpenCode - Edit ~/.config/opencode/opencode.json and add to the mcp section:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"houdini": {
"type": "local",
"command": [
"/Users/YOUR_USERNAME/Library/Preferences/houdini/20.5/houdini-mcp-server/venv/bin/python",
"/Users/YOUR_USERNAME/Library/Preferences/houdini/20.5/houdini-mcp-server/python/houdini_mcp_server.py"
],
"enabled": true
}
}
}
More info at official opencode docs.
Claude Desktop (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"houdini": {
"command": "/Users/YOUR_USERNAME/Library/Preferences/houdini/20.5/houdini-mcp-server/venv/bin/python",
"args": [
"/Users/YOUR_USERNAME/Library/Preferences/houdini/20.5/houdini-mcp-server/python/houdini_mcp_server.py"
]
}
}
}
Usage
- Start Houdini and click the "Start MCP" shelf button
- Start your AI client (OpenCode, Claude Desktop, etc.) and make sure that Houdini MCP is enabled (in opencode
/mcps) - Make a prompt with Houdini in mind to control Houdini
Examples
Randomize poins
For each scattered point randomize its size, rotation on Y and color.
This will most likely create a wrangler node with necessary expressions.
Making special effects
On currently selected point wrangler write vex that will display geometry by a wave that pass trough it as I scrub the timeline. Allow for editing wave amplitude, frequency, timing etc.
Available Tools
execute_python- Run arbitrary Python code withhoumodule accessget_scene_info- Get hip file path, frame range, selected nodes, FPS, etc.
Requirements
- Houdini 20.5+ (tested on macOS)
- Python 3.11+
- MCP-compatible AI client
Architecture
AI Client ←→ MCP Server ←→ HTTP ←→ RPC Service ←→ Houdini
stdio (venv) :9876 (inside Houdini)
houdini_mcp_server.py- Runs outside Houdini in venv, handles MCP protocolhoudini_rpc_service.py- Runs inside Houdini, executes code withhoumodule access
Uses HTTP bridge because Houdini's asyncio implementation is incompatible with MCP SDK.
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。