# Coating Lab (pypi · coatinglab-mcp)

Real surface finishes for game gun models: sourced finishes, variants, wear baked from use

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- pypi · `coatinglab-mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/hpdkhoa-coatinglab-mcp/coatinglab-mcp.md), [page](https://verifymcp.io/servers/hpdkhoa-coatinglab-mcp/coatinglab-mcp)

## Channel facts

- Registry: `pypi`
- Package: `coatinglab-mcp`
- Version: `0.1.0`
- 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 2026-10-17.

- **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 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 52/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 719 tokens (~55/item across 13 items; 13 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**: 73/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 19% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 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 Coating Lab MCP server?

Coating Lab runs locally as a PyPI package, launched with uvx coatinglab-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-coatinglab-mcp -- uvx coatinglab-mcp
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "hpdkhoa-coatinglab-mcp": {
      "command": "uvx",
      "args": [
        "coatinglab-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 64)

First indexed and scored.

## MCP tools (13)

### `list_finishes` (~36 tokens)

Every finish: name, process, colour (sRGB hex), metallic, roughness, what it wears to, measured or estimated.

### `read_finish` (~26 tokens)

One finish in full, with its notes and sources.

Input parameters:

- `finish` (string, required)

### `check_library` (~29 tokens)

The library against the physical rules: the finishes that break one, and why (empty: all hold).

### `check_finish` (~57 tokens)

A finish of your own against the rules before you add it.

Input parameters:

- `finish` (object, required): a finish: {name, substrates, base {linear, metallic, roughness}, worn_to, sources}
- `finish_id` (string)

### `list_wear_levels` (~33 tokens)

The wear levels (new, issued, worn, abused): each mask's threshold and what the level looks like.

### `list_templates` (~45 tokens)

The ready variant sets (e.g. ar15: issued, new_black, fde_two_tone, odg_ceramic, tungsten_stainless, abused_parkerized).

### `spec_for_modellab` (~61 tokens)

A coating spec for a Model Lab build: a template's variants on the slots it has, the wear zones from its marks.

Input parameters:

- `build` (string, required): a Model Lab build folder
- `template` (string)
- `variants`

### `describe_model` (~42 tokens)

Any model's meshes and material slots (an FBX), to write a coating spec for a model Model Lab did not make.

Input parameters:

- `fbx` (string, required)

### `validate_spec` (~38 tokens)

Every problem with a coating spec: a slot without a finish, a finish that does not go on its material.

Input parameters:

- `spec` (object, required)

### `bake` (~46 tokens)

Bakes the wear masks into a copy of the model (FBX for an engine, .blend for renders): about a minute.

Input parameters:

- `name`
- `spec` (object, required)

### `check_coating` (~36 tokens)

Each variant against its wear level's band, wear kept out of corners, every finish physical.

Input parameters:

- `bake_folder` (string, required)

### `render_variants` (~53 tokens)

Look-dev renders of the variants (labelled: not a game's view) and a sheet of them.

Input parameters:

- `bake_folder` (string, required)
- `variants`
- `views`: right, left, close

### `engine_params` (~39 tokens)

A variant's values by slot for an engine material that follows the shared wear formula.

Input parameters:

- `spec` (object, required)
- `variant` (string, required)

## Diagnostics

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

## Score history

- 2026-10-17: 64
- 2026-10-16: 64
- 2026-10-15: 64

## Common questions

### What is the Coating Lab MCP server?

Coating Lab is an MCP server listed in the public MCP registry as io.github.hpdkhoa/coatinglab-mcp. Real surface finishes for game gun models: sourced finishes, variants, wear baked from use. This page covers its PyPI package (coatinglab-mcp).

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

Coating Lab scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 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 Coating Lab MCP server expose?

Coating Lab exposes 13 tools: list_finishes, read_finish, check_library, check_finish, list_wear_levels, and 8 more. Their descriptions and schemas cost roughly 541 tokens of context every time the server is loaded.

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

Coating Lab is still listed as active in the MCP registry. We last reached this channel on 17 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 Coating Lab MCP server under?

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