dcc-mcp-houdini: Instructions file for Claude Code

CLAUDE.md

dcc-mcp-houdini CLAUDE.md is an instructions file for Claude Code from dcc-mcp/dcc-mcp-houdini. It costs 641 tokens per session, scanned A, original, MIT.

Instructions for connecting Claude Desktop or another compatible AI client to a server inside SideFX Houdini, a 3D graphics and visual-effects application. The connection exposes tools for inspecting scenes, creating nodes, running Houdini assets, and rendering.

In plain words
What is it for?
Use them to set up the Houdini connection, understand minimal and on-demand tool loading, and work with Houdini scenes, nodes, assets, and renders.
Why use it?
They explain how to configure the connection and how tools are loaded, so the client can use Houdini capabilities without loading every tool at startup.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is dcc-mcp/dcc-mcp-houdini's own configuration. It tells Claude Code how to work on dcc-mcp-houdini itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dcc-mcp-houdini configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dcc-mcp/dcc-mcp-houdini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dcc-mcp/dcc-mcp-houdini/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-houdini

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dcc-mcp-houdini CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dcc-mcp/dcc-mcp-houdini/claude-md/github.svg)](https://agentmods.dev/instructions/dcc-mcp/dcc-mcp-houdini/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dcc-mcp/dcc-mcp-houdini/claude-md"><img src="https://agentmods.dev/badge/instructions/dcc-mcp/dcc-mcp-houdini/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dcc-mcp-houdini CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dcc-mcp/dcc-mcp-houdini/claude-md"><img src="https://agentmods.dev/badge/instructions/dcc-mcp/dcc-mcp-houdini/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 641 This file is loaded in full into every session.
When invoked 641 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00641 $0.00641
Opus 5 $0.00320 $0.00320
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 9d ago against content hash 240ceb6b127f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dcc-mcp-houdini CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Desktop / Anthropic API Integration Guide

Claude-specific integration notes for dcc-mcp-houdini. For the full project map, see AGENTS.md.


What This Project Does

dcc-mcp-houdini embeds an MCP Streamable HTTP server directly inside SideFX Houdini. Claude Desktop (or any Anthropic API client using MCP) can call 180+ Houdini tools across 30 skill packages over HTTP — scene inspection, node authoring, HDA execution, rendering, and more.


Claude Desktop Configuration

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "houdini": {
      "url": "http://127.0.0.1:9765/mcp"
    }
  }
}

File locations:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

If running gateway mode, use http://127.0.0.1:9765/mcp instead.

Restart Claude Desktop after editing.


Progressive Loading — Important for Claude

By default, dcc-mcp-houdini starts in minimal mode with only 2 skills loaded:

  • houdini-scripting
  • houdini-scene

All other skills must be loaded on demand. When Claude needs a tool from an unloaded skill:

  1. Call load_skill("houdini-nodes") to expand the skill.
  2. Then call the typed tool (e.g., houdini_nodes__create_node).

Claude-Specific Tips

  • Viewport feedback: Ask Claude to call houdini_render__capture_viewport after scene changes. The base64 PNG lets Claude "see" the current state.
  • Node networks: Claude excels at building SOP/OBJ networks. Chain create_nodeset_node_parmsconnect_nodescook_node.
  • Code execution: Prefer search_skillsload_skill → typed tools. Use execute_python only as last resort.
  • HDA automation: Use houdini_hda_automation__instantiate_hda and houdini_hda_automation__cook_top_network for HDA workflows.
  • Cancellation: Claude can send notifications/cancelled for long renders.

Quick Test Prompts

Read the full file on GitHub · 75 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 75 lines · 641 tokens per session scan A 240ceb6b127f

Subscribe to this mod's changes

dcc-mcp-houdini CLAUDE.md is an instructions file published in the GitHub repository dcc-mcp/dcc-mcp-houdini (12 stars, last pushed 2d ago), licensed MIT. It adds 641 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens