vrm-toolkit-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VRM_TOOLKIT_CHROME | No | Path to a Chrome or Edge executable, used by vrma_preview and vrm_snapshot. Overrides auto-detection. | |
| VRM_TOOLKIT_MAX_BYTES | No | Maximum input file size in bytes. Default is 512 MiB (536870912 bytes). |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| vrm_inspectA | Inspect a local VRM file (0.x or 1.0): meta including license/permission fields, humanoid bone map, expressions/blendshapes, polygon and texture statistics. Structured JSON output; no rendering. |
| vrm_validateA | Validate a local VRM file and return a finding list: missing required humanoid bones, broken node references, missing meta/license fields, unrecognized required extensions, and configurable size/triangle/texture/material budget checks. |
| vrma_inspectA | Inspect a local VRMA (VRM animation) file: spec version, targeted humanoid bones, expression tracks, channel counts, duration, and an estimated frame rate. Structured JSON output; no rendering. |
| vrma_previewA | Render a VRMA animation applied to a VRM through a local headless Chrome/Edge. mode=image writes a PNG at time_sec; mode=video records a short WebM clip (max 10 seconds). |
| vrm_snapshotA | Render a still PNG of a VRM in its rest pose through a local headless Chrome/Edge, with optional expression weights (e.g. {"happy": 1}) and view presets including a face close-up. |
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 5 tools
Each tool targets a distinct file type and operation: VRM inspect vs validate, VRMA inspect vs preview, and VRM snapshot for rendering. There is no overlap in purpose, making selection unambiguous.
All tool names follow a consistent pattern of a file-format prefix (vrm/vrma) followed by an action word (inspect, validate, preview, snapshot). The pattern is uniform and predictable, with only a minor noun/verb nuance that does not cause confusion.
Five tools is an ideal size for a focused VRM toolkit, covering inspection, validation, and rendering without unnecessary bulk. Each tool appears necessary and well-scoped.
The toolkit covers the core workflows for VRM/VRMA files: inspecting, validating, previewing animations, and rendering snapshots. The only minor gap is the lack of a dedicated VRMA validation tool, but this does not critically hinder the overall purpose.