# Model Lab (pypi · modellab-mcp)

Draws rigged game gun models in Blender from parameters, checked against the real gun

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- pypi · `modellab-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/hpdkhoa-modellab-mcp/modellab-mcp.md), [page](https://verifymcp.io/servers/hpdkhoa-modellab-mcp/modellab-mcp)

## Channel facts

- Registry: `pypi`
- Package: `modellab-mcp`
- Version: `0.2.0`
- 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 2026-10-16.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 29 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 1 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 981 tokens (~98/item across 10 items; 10 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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (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

### How do I install the Model Lab MCP server?

Model Lab runs locally as a PyPI package, launched with uvx modellab-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add hpdkhoa-modellab-mcp -- uvx modellab-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "hpdkhoa-modellab-mcp": {
      "command": "uvx",
      "args": [
        "modellab-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "hpdkhoa-modellab-mcp": {
      "command": "uvx",
      "args": [
        "modellab-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add hpdkhoa-modellab-mcp -- uvx modellab-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hpdkhoa-modellab-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "modellab-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add hpdkhoa-modellab-mcp --command uvx --arg modellab-mcp
```

### Hermes

```yaml
mcp_servers:
  hpdkhoa-modellab-mcp:
    command: "uvx"
    args: ["modellab-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "hpdkhoa-modellab-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "modellab-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add hpdkhoa-modellab-mcp -t stdio -c uvx -a modellab-mcp
```

### Other

```json
{
  "mcpServers": {
    "hpdkhoa-modellab-mcp": {
      "command": "uvx",
      "args": [
        "modellab-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.

### 2026-10-15 (score 69, +30)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100
- [functional] Package version: 0.1.0 → 0.2.0

### 2026-10-14 (score 39)

First indexed and scored.

## MCP tools (10)

### `list_platforms` (~22 tokens)

The gun families Model Lab can draw, with their parameter names.

### `describe_params` (~48 tokens)

A platform's parameters (type, range or choices, unit, meaning) and the sources its real numbers come from.

Input parameters:

- `platform` (string): a platform id, e.g. ar15

### `list_presets` (~52 tokens)

The ready guns (M4A1, M16A2, AR15, M4A1_Kitted, AR15_Optic): their parameters and the published lengths each
build is checked against.

### `list_attachments` (~70 tokens)

The attachments a build can mount on the rails and M-LOK slots (optics, backup sights, the carry handle, a
vertical grip, a light): what each is, the rails it fits, its states and moving parts. Pass them to build_gun as
params.attachments.

### `list_references` (~36 tokens)

The real-gun photos compare_to_reference measures against: each photo's source, licence, scale and the build
that matches it.

### `build_gun` (~195 tokens)

Builds a gun in Blender (15 to 30 s): the rig FBX, the hand magazine FBX, one FBX an attachment, the .blend
(with the cycle as an action), facts.json and a sheet of labelled dev views; with motion, GIFs of the cycle.
Returns the checks that failed (none when all_pass), the size and the files.

Input parameters:

- `motion` (boolean): also render the moving parts' cycle as GIFs (about a minute more)
- `name`: the model's name in its files (letters, digits, _)
- `params`: parameters to set or change, e.g. {"barrel_in": 16}
- `platform`: without a preset: the platform to build
- `preset`: a preset to start from, e.g. M4A1
- `scale` (number): the whole model's scale; 1 is real size

### `build_gun_clips` (~148 tokens)

The gun's own clips on a build's rig, from real beats and timings at 60 frames a second: each measured (parts on
their axes, the bolt's stroke, the cover open before the carrier, the magazine out of the well and seated, the bolt
held on its catch), exported alone as FBX (A_<name>_<clip>.fbx) and shown as a GIF.

Input parameters:

- `build` (string, required): a build folder name from list_builds
- `clips`: charge, chamber_check, fire, fire_last, reload, reload_empty, stock; leave out for all
- `render` (boolean): render a labelled GIF a clip

### `compare_to_reference` (~119 tokens)

The real-gun check: draws the build's side outline at the reference photo's scale and alignment, measures both
outlines column by column, and returns the stretches that differ by more than 0.4 cm, each with the parts there
and its zone (the gun, or an attachment over the rail), and an overlay picture (the model in red over the photo).

Input parameters:

- `build`: a build folder; leave out to build the reference's own configuration
- `reference` (string): a reference id from list_references

### `list_builds` (~25 tokens)

The latest builds, newest first: name, whether every check passed, size.

### `read_build` (~48 tokens)

A build's facts: parameters, marks, moving parts, rails, attachments, the parts table, every check, files.

Input parameters:

- `build` (string, required): a build folder name from list_builds

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/hpdkhoa-modellab-mcp/modellab-mcp#diagnostics

## Score history

- 2026-10-16: 69
- 2026-10-15: 69
- 2026-10-14: 39

## Common questions

### What is the Model Lab MCP server?

Model Lab is an MCP server listed in the public MCP registry as io.github.hpdkhoa/modellab-mcp. Draws rigged game gun models in Blender from parameters, checked against the real gun. This page covers its PyPI package (modellab-mcp).

### Is the Model Lab MCP server safe to use?

Model Lab scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Model Lab MCP server expose?

Model Lab exposes 10 tools: list_platforms, describe_params, list_presets, list_attachments, list_references, and 5 more. Their descriptions and schemas cost roughly 763 tokens of context every time the server is loaded.

### Is the Model Lab MCP server still maintained?

Model Lab is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Model Lab MCP server under?

Model Lab declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/modellab-mcp/
- Socket report: https://socket.dev/pypi/package/modellab-mcp
- Repository: https://github.com/hpdkhoa/modellab-mcp
- Changelog RSS feed: https://verifymcp.io/servers/hpdkhoa-modellab-mcp/modellab-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/hpdkhoa-modellab-mcp/modellab-mcp.json
- HTML version of this page: https://verifymcp.io/servers/hpdkhoa-modellab-mcp/modellab-mcp