MoonRay MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MOONRAY_MCP_RUNTIME | No | The absolute path to the staged MoonRay Houdini runtime. | ~/.local/share/moonray-mcp/runtime |
| MOONRAY_MCP_USD_TO_RDL | No | Optional path to the USD-to-RDL translator executable, overriding the default. | |
| MOONRAY_MCP_NATIVE_HOST | No | Optional path to a controllable hd_render build; otherwise the server looks for bin/hd_render inside the staged runtime. | |
| MOONRAY_MCP_OUTPUT_ROOT | No | The absolute path to the directory where render jobs and reports are stored. | ~/.local/share/moonray-mcp/jobs |
| MOONRAY_MCP_SETUP_SCRIPT | No | Optional path to the runtime setup script, overriding the expected default. | |
| MOONRAY_ZELTNER_FIXTURE_ROOT | No | Path to external image set used by the Zeltner regression example. | |
| MOONRAY_MCP_INTERACTIVE_VIEWER | No | Optional path to the standalone viewer executable, overriding the default. |
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 |
|---|---|
| moonray_healthC | Check the staged runtime, required tools, and MoonRay Hydra delegate. |
| moonray_capabilitiesB | Describe the scene types, backend, reports, and controls in this build. |
| moonray_resourcesA | Check memory, disk, CPU load, and conflicting renders before launch. |
| launch_interactive_viewerC | Open a scene in MoonRay's visible standalone interactive viewer. |
| interactive_viewer_statusB | Report whether a standalone MoonRay viewer window is still active. |
| switch_interactive_viewer_aovA | Switch a live standalone viewer to beauty, albedo, normal, depth, or wireframe. |
| set_interactive_viewer_exposureA | Set the live standalone viewer display exposure from -20 to 20 stops. |
| set_interactive_viewer_denoisingA | Turn live standalone viewer denoising explicitly on or off. |
| capture_interactive_viewer_snapshotB | Save the viewer as a raw EXR and a display-referred PNG. |
| interactive_viewer_previewC | Return the visible standalone viewer image directly to the MCP client. |
| stop_interactive_viewerA | Close a standalone MoonRay viewer owned by this MCP process. |
| validate_sceneB | Preflight a USD or RDL scene before committing to a render. |
| inspect_sceneB | Summarize a USD stage and recommend an authored camera for rendering. |
| inspect_materialsC | Inspect source materials, textures, and a job's translated MoonRay RDL. |
| start_renderC | Start an asynchronous MoonRay render and immediately return its job ID. |
| render_statusB | Return the current phase, elapsed time, diagnostics, and output paths. |
| cancel_renderA | Cancel a queued or active render without leaving an orphan process. |
| pause_renderC | Pause an active native-host render through MoonRay's Hydra delegate. |
| resume_renderC | Resume an active native-host render through MoonRay's Hydra delegate. |
| resume_from_checkpointC | Start a new native render job from a completed checkpoint EXR. |
| capture_render_snapshotB | Request a current-frame EXR and PNG preview from a native-host render. |
| render_previewA | Return the newest live snapshot, or the final preview after completion. |
| render_resultC | Return a completed job report and its PNG preview when available. |
| compare_rendersB | Compare two completed job IDs or image paths and return a difference image. |
| run_comparison_manifestB | Run a saved image-comparison manifest and preserve aggregate results. |
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
Each tool targets a distinct action and resource: viewer controls, scene inspection, render lifecycle, and comparison are clearly separated. Even similar-sounding tools like capture_interactive_viewer_snapshot and capture_render_snapshot are differentiated by their target context.
The set mixes verb-first names like start_render and validate_scene with noun-first names like render_status and moonray_resources. The pattern is readable, but it is not fully consistent; some query tools would be clearer with a get_ or list_ prefix.
At 25 tools, the surface is on the heavy end, though the breadth of MoonRay workflows partially justifies it. The tools cluster into coherent subdomains, but the overall count feels somewhat large for an MCP server.
The set covers the core render lifecycle, interactive viewer controls, scene preflight, and comparison workflows. Minor gaps include no explicit render job listing or general render-setting adjustment, but agents can work around these with existing status and capability tools.