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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.