Best for
- VFX artists and TDs who want to accelerate Houdini workflows with AI assistants
- Users needing procedural modeling and simulation setup
- Users familiar with Houdini but wanting to automate repetitive tasks
This is a feature-rich MCP server that exposes Houdini's powerful capabilities through a natural language interface to AI. Its extensive toolset covers almost all major Houdini contexts, making it suitable for VFX artists and TDs. However, attention must be paid to security and performance overhead.
Strongest · Documentation 15/20 Weakest · Reliability 11/20
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Runtime:Python 3.10+
HOUDINI_HOST
Houdini host read by the MCP server process, default localhost; set in your MCP client, not the Houdini package file.
HOUDINI_PORT
hwebserver port read by the MCP server process, default 8100; pinning it disables the 8100-8115 port scan.
FXHOUDINIMCP_PORT
Port the Houdini plugin listens on, default 8100; set in the Houdini package file and keep in sync with HOUDINI_PORT.
FXHOUDINIMCP_AUTOSTART
Auto-start the plugin server when the UI is ready, default 1; set 0 to disable. Lives in the Houdini package file.
FXHOUDINIMCP_AUTO_LAYOUT
Automatic node layout, default 1; set 0 to preserve manual layouts. Lives in the Houdini package file.
FXHOUDINIMCP_BIND
Address the plugin binds, default 127.0.0.1; the bridge runs arbitrary Python with no authentication, so only widen on a trusted network.
MCP_TRANSPORT
MCP transport, stdio or streamable-http, default stdio; set in your MCP client.
LOG_LEVEL
Logging level, default INFO; set in your MCP client.
pip install fxhoudinimcppython -m fxhoudinimcp install{
"mcpServers": {
"fxhoudini": {
"command": "C:\\\\Program Files\\\\Python311\\\\python.exe",
"args": [
"-m",
"fxhoudinimcp"
]
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"fxhoudini": {
"command": "C:\\\\Program Files\\\\Python311\\\\python.exe",
"args": [
"-m",
"fxhoudinimcp"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add fxhoudini -- 'C:\\Program Files\\Python311\\python.exe' -m fxhoudinimcp
Run it in a terminal; replace any <…> placeholders with your own values first.
After installing, restart Houdini and your MCP client and check that an MCP menu appears in Houdini's menu bar; then call get_scene_info or get_houdini_connection_status from your client — structured info about the running Houdini session confirms the bridge works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
A comprehensive Model Context Protocol (MCP) 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. Offers 188 tools, 8 resources, and 9 prompts serving 31 written workflow guides.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision 76d96cf0df18 Data synced 2026-10-12 Read the FMRS scoring method