"Houdini" matching MCP servers:

Enables language models to inspect the current Houdini scene, create and modify nodes, and run VEX/Python code in the running Houdini session via MCP.

Enables MCP clients to drive a live Houdini session over TCP, supporting scene inspection, cooking, rendering, and code execution in Houdini 22.

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.

Enables AI assistants and CLI tools to read and control Houdini scenes with a safety model that separates read and write operations.

MCP server exposing a live Houdini session for inspecting and debugging the DazToHue pipeline, currently providing a read-only ping tool with authenticated, loopback-only access.

Drive SideFX Houdini from any agent: build node networks in one all-or-nothing call, cook, render, capture the viewport, and read the offline docs of your Houdini build. 20 tools with modes.

Multi-protocol IPC adapter layer for integrating DCC software (Maya, Houdini, Blender, Unreal, Unity) with MCP, enabling tool registration and remote control across multiple transport protocols.

Enables an AI agent to find, screenshot, GIF-record and drive Qt widgets inside running Qt applications and DCCs such as Houdini, Blender, Maya and Nuke, working across PySide6, PyQt6, PySide2 and PyQt5. It routes one agent connection to many applications at once, offering semantic widget search, widget-tree inspection, clicking/typing, and per-window or per-panel captures.

Houtini LM - LM Studio MCP Server with Expert Prompt Library and Custom Prompting - Offload tasks to LM Studio from Claude Desktop.

Lets Claude Code or any MCP client hand bounded work such as code review, boilerplate generation, commit messages, and format conversion to a local GPU model, an OpenAI-compatible cloud API, or a LiteLLM/OpenRouter router, so those files never enter the orchestrator's context window. This cuts token cost by roughly 93% on read-heavy tasks and provides a second model for reviewing code, while the main AI platform keeps the planning and judgement calls.

Enables Claude Code and other MCP clients to delegate bounded tasks such as code review, boilerplate generation, commit messages, and format conversion to a local or cloud OpenAI-compatible LLM. It keeps the main model as architect while cutting token costs by sending files and prompts straight to the second model instead of into the orchestrator's context window.

It enables Claude or any MCP client to delegate bounded tasks such as code review, boilerplate generation, commit messages, format conversion, and embeddings to local or cloud OpenAI-compatible LLMs, reducing token usage and providing a second opinion.

Enables Claude Code and other MCP clients to hand bounded work — code review, test stubs, commit messages, docs, format conversion, mock data, embeddings — to a local GPU model or a cheap cloud/OpenAI-compatible endpoint, so file contents are sent straight to that model instead of entering the main AI platform's context window. This cuts token spend dramatically while giving users a second model for reviewing code, with the orchestrating assistant still checking every result.

Enables Claude Code and other MCP clients to offload bounded work — code review, boilerplate, commit messages, format conversion, embeddings — to a local or cloud OpenAI-compatible LLM, cutting token spend by keeping large files out of the orchestrator's context. It also provides a second model for reviewing code and drafting tasks while the main assistant retains planning and QA.

Enables Claude and other MCP clients to hand off bounded work — code review, test stubs, boilerplate, commit messages, docs, format conversion, embeddings — to local or cloud OpenAI-compatible models while the main assistant keeps planning and QA. Keeps large source files out of the orchestrator's context window, cutting token costs and providing a cheap second opinion on code.

Enables Claude Code and other MCP clients to offload bounded tasks to a local or cloud LLM (LM Studio, Ollama, vLLM, LiteLLM, OpenRouter, DeepSeek, Groq, Cerebras, OpenAI) so files are read and drafted outside the orchestrator's context window, cutting token costs. It also provides a cheap second model for code review, test stubs, commit messages, format conversion, and embeddings.

Enables Claude or other MCP clients to offload bounded tasks such as code review, boilerplate, commit messages, and format conversion to local or cloud OpenAI-compatible models, saving tokens and providing a second opinion. It supports endpoints including LM Studio, Ollama, vLLM, OpenRouter, OpenAI, DeepSeek, Groq, and Cerebras.

Enables MCP clients such as Claude Code to delegate bounded tasks like code review, boilerplate generation, commit messages, format conversion, and embeddings to local or cloud OpenAI-compatible LLMs, reducing token costs while keeping the main model in control.

Enables Claude or other MCP clients to delegate bounded coding work—such as code review, test stubs, commit messages, format conversion, and embeddings—to local or cloud OpenAI-compatible models while reducing token usage. It keeps the main AI platform as the orchestrator and has returned work reviewed by that platform.

Enables MCP clients such as Claude Code to hand bounded tasks — code review, test stubs, boilerplate, commit messages, format conversion and embeddings — to a local GPU model or a cheaper cloud or router endpoint over any OpenAI-compatible API, so bulky file content never enters the orchestrator's context window. The primary model stays the architect and QA, while token spend drops and a second model becomes available for reviewing code on demand.