HoudiniMCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_scene_infoC | Ask Houdini for scene info. Returns JSON as a string. |
| create_nodeC | Create a new node in Houdini (example). |
| execute_houdini_codeC | Execute arbitrary Python code in Houdini's environment. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a distinct purpose: getting scene info, creating a node, and executing arbitrary code. No overlap in functionality, so an agent can easily differentiate them.
All tools follow a consistent verb_noun pattern: get_scene_info, create_node, execute_houdini_code. No mixing of conventions or vague verbs.
With only 3 tools, the server feels thin for a comprehensive Houdini integration. However, the generic execute_houdini_code tool expands the scope, making the count borderline acceptable.
The tool surface is severely incomplete for typical Houdini workflows (e.g., no delete, modify, or connect node tools). The execute_houdini_code tool provides a workaround but undermines the purpose of dedicated tools.