fxhoudinimcp

The most comprehensive MCP server for SideFX Houdini.
167 tools across 19 categories, covering every major Houdini context.

                    

Table of Contents

• About
• Features
• Architecture
• Installation
• Usage
• Environment Variables
• Development
• Contact

About

A comprehensive MCP (Model Context Protocol) server for SideFX Houdini. Connects AI assistants like Claude directly to Houdini's Python API, enabling natural language control over scene building, simulation setup, rendering, and more.

167 tools, 8 resources, and 6 workflow prompts out of the box.

Features

Category	Tools	Description
Scene Management	7	Open, save, import/export, scene info
Node Operations	16	Create, delete, copy, connect, layout, flags
Parameters	10	Get/set values, expressions, keyframes, spare parameters
Geometry (SOPs)	12	Points, prims, attributes, groups, sampling, nearest-point search
LOPs/USD	18	Stage inspection, prims, layers, composition, variants, lighting
DOPs	8	Simulation info, DOP objects, step/reset, memory usage
PDG/TOPs	10	Cook, work items, schedulers, dependency graphs
COPs (Copernicus)	7	Image nodes, layers, VDB data
HDAs	10	Create, install, manage Digital Assets and their sections
Animation	9	Keyframes, playbar control, frame range
Rendering	9	Viewport capture, render nodes, settings, render launch
VEX	5	Create/edit wrangles, validate VEX code
Code Execution	4	Python, HScript, expressions, env variables
Viewport/UI	10	Pane management, screenshots, error detection
Scene Context	8	Network overview, cook chain, selection, scene summary, error analysis
Workflows	8	One-call Pyro/RBD/FLIP/Vellum setup, SOP chains, render config
Materials	4	List, inspect, create materials and shader networks
CHOPs	4	Channel data, CHOP nodes, export channels to parameters
Cache	4	List, inspect, clear, write file caches
Takes	4	List, create, switch takes with parameter overrides

Architecture

flowchart LR
    subgraph Client[" 🤖 AI Client "]
        direction TB
        A1("Claude Desktop")
        A2("Cursor / VS Code")
        A3("Claude Code")
    end

    subgraph MCP[" ⚡ FXHoudini MCP Server "]
        direction TB
        B1("🔧 167 Tools")
        B2("📦 8 Resources")
        B3("💬 6 Prompts")
    end

    subgraph Houdini[" 🔶 SideFX Houdini "]
        direction TB
        C1("🌐 hwebserver")
        C2("📡 Dispatcher")
        C3("🎛️ hou.* Handlers")
        C1 --> C2 --> C3
    end

    Client -. "MCP Protocol · stdio" .-> MCP
    MCP -. "HTTP / JSON · port 8100" .-> Houdini

    classDef clientBox fill:#f0f4ff,stroke:#b8c9e8,stroke-width:1px,color:#2d3748,rx:12,ry:12
    classDef mcpBox fill:#eef6f0,stroke:#a8d5b8,stroke-width:1px,color:#2d3748,rx:12,ry:12
    classDef houdiniBox fill:#fff5f0,stroke:#e8c4a8,stroke-width:1px,color:#2d3748,rx:12,ry:12

    classDef clientNode fill:#dbe4f8,stroke:#96b0dc,stroke-width:1px,color:#2d3748,rx:8,ry:8
    classDef mcpNode fill:#d4edda,stroke:#82c896,stroke-width:1px,color:#2d3748,rx:8,ry:8
    classDef houdiniNode fill:#fde4d0,stroke:#e0a87c,stroke-width:1px,color:#2d3748,rx:8,ry:8

    class Client clientBox
    class MCP mcpBox
    class Houdini houdiniBox
    class A1,A2,A3 clientNode
    class B1,B2,B3 mcpNode
    class C1,C2,C3 houdiniNode

Loading

Uses Houdini's built-in hwebserver. No custom socket servers, no rpyc. Uses hdefereval.executeInMainThreadWithResult() to safely run hou.* calls on the main thread.

Installation

Requirements

• Houdini 20.5+ (tested on 21.0)
• Python 3.10+
• MCP SDK (mcp package) 1.8+

1. Install the MCP Server

From PyPI:

pip install fxhoudinimcp

From source:

pip install -e .

Or with development dependencies:

pip install -e ".[dev]"

2. Install the Houdini Plugin

Option A: Houdini package (recommended)

1. Copy houdini/fxhoudinimcp.json to your Houdini packages directory:

   • Windows: %USERPROFILE%/Documents/houdiniXX.X/packages/
   • Linux: ~/houdiniXX.X/packages/
   • macOS: ~/Library/Preferences/houdini/XX.X/packages/

2. Edit the JSON file to set FXHOUDINIMCP to point to the houdini directory in this repo.

Option B: Manual copy

Copy the contents of houdini/ into your Houdini user preferences directory so that:

• scripts/python/fxhoudinimcp_server/ is on Houdini's Python path
• scripts/456.py runs on scene load
• toolbar/fxhoudinimcp.shelf appears in your shelf

3. Configure Your MCP Client

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "fxhoudini": {
      "command": "python",
      "args": ["-m", "fxhoudinimcp"],
      "env": {
        "HOUDINI_HOST": "localhost",
        "HOUDINI_PORT": "8100"
      }
    }
  }
}

Claude Code (.mcp.json in project root):

{
  "mcpServers": {
    "fxhoudini": {
      "command": "python",
      "args": ["-m", "fxhoudinimcp"],
      "env": {
        "HOUDINI_HOST": "localhost",
        "HOUDINI_PORT": "8100"
      }
    }
  }
}

Tip

If Claude Desktop reports the server as disconnected, replace "python" with the full absolute path to your Python executable. Claude Desktop does not always inherit your system PATH. Find it with:

python -c "import sys; print(sys.executable)"

Then use the result in your config, e.g. "command": "C:\\Program Files\\Python311\\python.exe". After any config change, fully quit Claude Desktop (system tray → Quit) and relaunch.

Usage

Launch Houdini normally. The plugin auto-starts on scene load (controlled by FXHOUDINIMCP_AUTOSTART env var). You can also toggle it manually via the MCP Server shelf tool.

Once connected, your AI assistant can:

"Create a procedural rock generator with mountain displacement"
"Set up a Pyro simulation with a sphere source"
"Build a USD scene with a camera, dome light, and ground plane"
"Create an HDA from the selected subnet"
"Debug why my scene has cooking errors"

Environment Variables

Variable	Default	Description
HOUDINI_HOST	localhost	Houdini host address
HOUDINI_PORT	8100	Houdini hwebserver port
FXHOUDINIMCP_PORT	8100	Port for the Houdini plugin to listen on
FXHOUDINIMCP_AUTOSTART	1	Set to 0 to disable auto-start
MCP_TRANSPORT	stdio	MCP transport (stdio or streamable-http)
LOG_LEVEL	INFO	Logging level

Development

# Install dev dependencies
pip install -e ".[dev]"

# Run linter
ruff check python/

# Run tests
pytest

How It Works

1. Houdini Plugin (houdini/): Runs inside Houdini's Python environment. Registers @hwebserver.apiFunction endpoints that receive JSON commands. Uses hdefereval.executeInMainThreadWithResult() to safely execute hou.* calls on the main thread.

2. MCP Server (python/fxhoudinimcp/): A standalone Python process using FastMCP. Exposes 167 tools, 8 resources, and 6 prompts via the MCP protocol. Forwards tool calls to Houdini over HTTP.

3. Bridge (python/fxhoudinimcp/bridge.py): Async HTTP client that sends commands to Houdini's hwebserver and deserializes responses. Handles connection errors and timeouts.

Contact

Project Link: fxhoudinimcp

                       

License

MIT