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
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.