# io.github.dwarehouse1/vrm-toolkit-mcp (npm · vrm-toolkit-mcp)

Inspect, validate and preview VRM / VRMA files from an AI agent (5 tools, local stdio server).

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-07

## Components

- npm · `vrm-toolkit-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/dwarehouse1-vrm-toolkit-mcp/vrm-toolkit-mcp.md), [page](https://verifymcp.io/servers/dwarehouse1-vrm-toolkit-mcp/vrm-toolkit-mcp)

## Channel facts

- Registry: `npm`
- Package: `vrm-toolkit-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-07.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 49 of 187 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 520 tokens (~104/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add dwarehouse1-vrm-toolkit-mcp -- npx -y vrm-toolkit-mcp
```

### Codex

```bash
codex mcp add dwarehouse1-vrm-toolkit-mcp -- npx -y vrm-toolkit-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dwarehouse1-vrm-toolkit-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "vrm-toolkit-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dwarehouse1-vrm-toolkit-mcp --command npx --arg -y --arg vrm-toolkit-mcp
```

### Hermes

```yaml
mcp_servers:
  dwarehouse1-vrm-toolkit-mcp:
    command: "npx"
    args: ["-y", "vrm-toolkit-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "dwarehouse1-vrm-toolkit-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "vrm-toolkit-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-07 (score 66, +3)

- [security improvement] Known CVEs: partial → pass
- [functional] Dependency health: partial → 0.89

### 2026-08-06 (score 63, +27)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 67
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: pass

### 2026-08-05 (score 36)

First indexed and scored.

## MCP tools (5)

### `vrm_inspect` (~70 tokens)

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.

Input parameters:

- `path` (string, required): Local path to a .vrm file

### `vrm_validate` (~77 tokens)

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.

Input parameters:

- `limits` (object): Optional budget overrides
- `path` (string, required): Local path to a .vrm file

### `vrma_inspect` (~66 tokens)

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.

Input parameters:

- `path` (string, required): Local path to a .vrma file

### `vrma_preview` (~181 tokens)

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).

Input parameters:

- `duration_sec` (number): Video mode: recording length
- `fps` (integer): Video mode: capture rate (default 30)
- `height` (integer)
- `mode` (string): Default image
- `output_path` (string, required): Where to write the PNG/WebM output
- `time_sec` (number): Image mode: clip time to render (default mid-clip)
- `view` (string)
- `vrm_path` (string, required): Local path to the .vrm avatar
- `vrma_path` (string, required): Local path to the .vrma animation
- `width` (integer)

### `vrm_snapshot` (~126 tokens)

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.

Input parameters:

- `expression` (object)
- `height` (integer)
- `output_path` (string, required): Where to write the PNG output
- `path` (string, required): Local path to the .vrm avatar
- `pose` (string): v0.1 supports the rest pose only
- `view` (string)
- `width` (integer)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/dwarehouse1-vrm-toolkit-mcp/vrm-toolkit-mcp#diagnostics

## Score history

- 2026-08-07: 66
- 2026-08-06: 63
- 2026-08-05: 36

## Links

- npm package: https://www.npmjs.com/package/vrm-toolkit-mcp
- Socket report: https://socket.dev/npm/package/vrm-toolkit-mcp
- Repository: https://github.com/dwarehouse1/vrm-toolkit-mcp
- Changelog RSS feed: https://verifymcp.io/servers/dwarehouse1-vrm-toolkit-mcp/vrm-toolkit-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dwarehouse1-vrm-toolkit-mcp/vrm-toolkit-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dwarehouse1-vrm-toolkit-mcp/vrm-toolkit-mcp