ca-scene-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CA_SCENE_WORKSPACE | No | Directory to store scene files. Defaults to .ca-scenes. | .ca-scenes |
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_capabilitiesC | Describe supported objects, actions, solvers, and outputs. |
| get_scene_schemaA | Return the discriminated JSON schema for scene IR version 2. |
| create_sceneC | Create an empty animation scene. |
| list_scenesA | List all animation scenes in the workspace. |
| get_sceneB | Read a complete animation scene. |
| set_cameraC | Set a fixed look-at camera; position and target use metres. |
| apply_scene_patchB | Transactionally apply a recursive merge patch to a scene. |
| add_objectC | Add a rigid body, cloth, smoke/liquid fluid, or compound container. |
| add_constraintB | Add a constraint; spec.kind is fixed-point or distance. |
| add_fieldB | Add a force or acceleration field; spec.kind is uniform or radial. |
| add_actionB | Add a transform, impulse, force, or fluid emission action. |
| update_objectC | Update one object; patch.kind must match its existing object kind. |
| update_constraintB | Update one constraint; patch.kind must match its existing constraint kind. |
| update_fieldC | Update one field; patch.kind must match its existing field kind. |
| update_actionB | Update one action; patch.kind must match its existing action kind. |
| remove_itemC | Remove one scene item when it has no remaining references. |
| simulate_sceneC | Validate and submit a scene to the configured Newton executor. |
| validate_sceneC | Return structured errors, suggestions, and resource estimates. |
| preview_sceneB | Run a short low-cost preview and return keyframes and metrics. |
| run_sceneC | Submit a persistent simulation and rendering bundle asynchronously. |
| get_jobC | Poll an asynchronous scene job. |
| cancel_jobC | Cancel a queued scene job. |
| render_sceneC | Validate and submit a scene to the configured Newton renderer. |
| export_sceneC | Export a scene; the initial executor supports JSON. |
| export_programC | Export a standalone Python program and matching scene JSON. |
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 25 tools
Most tools have distinct purposes, but simulate_scene and run_scene could be confused (both involve submission to Newton executor/renderer). Other tools are clearly separated.
All tools follow a consistent verb_noun pattern in snake_case (e.g., add_action, update_object, validate_scene). No mixing of styles.
25 tools is high but still reasonable given the broad domain covering objects, actions, constraints, fields, simulation, rendering, export, and job management. Slightly above ideal but not chaotic.
Covers most lifecycle operations: create, read, update, delete for items, plus actions/constraints/fields. Notable missing tool to delete an entire scene, though apply_scene_patch may cover it indirectly.