# melta UI (npm · melta-ds-mcp)

AI-Ready design system MCP: melta UI tokens, component contracts, 99 rules, check_html self-verify

- Trust score: 70/100 (medium)
- Change this week: +17
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `melta-ds-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/tsubotax-melta-ui/melta-ds-mcp.md), [page](https://verifymcp.io/servers/tsubotax-melta-ui/melta-ds-mcp)

## Channel facts

- Registry: `npm`
- Package: `melta-ds-mcp`
- Version: `1.3.0`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (105 of 109), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (105 of 109), so this covers what we could see, not the whole tree.
- **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 14 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 547 tokens (~54/item across 10 items; 6 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add tsubotax-melta-ui -- npx -y melta-ds-mcp
```

### Codex

```bash
codex mcp add tsubotax-melta-ui -- npx -y melta-ds-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tsubotax-melta-ui": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "melta-ds-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tsubotax-melta-ui --command npx --arg -y --arg melta-ds-mcp
```

### Hermes

```yaml
mcp_servers:
  tsubotax-melta-ui:
    command: "npx"
    args: ["-y", "melta-ds-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "tsubotax-melta-ui": {
      "command": "npx",
      "args": [
        "-y",
        "melta-ds-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.

### 2026-08-02 (score 70, +44)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 26, +21)

- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 5, −48)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (6)

### `get_token` (~66 tokens)

Get a design token by dot-path. Returns the token object with value and tailwind class.

Input parameters:

- `path` (string, required): Dot-separated path to the token (e.g. "color.primary.600", "spacing.4", "radius.lg", "typography.fontSize.base")

### `get_component` (~47 tokens)

Get component metadata including variants, sizes, accessibility requirements, and HTML sample.

Input parameters:

- `id` (string, required): Component ID (e.g. "button", "card", "table", "sidebar")

### `check_rule` (~55 tokens)

Check Tailwind classes against melta UI prohibition rules. Returns violations with reasons and alternatives.

Input parameters:

- `classes` (string, required): Space-separated Tailwind classes to check (e.g. "text-black shadow-2xl bg-green-500")

### `check_html` (~131 tokens)

Lint a full HTML/JSX source against melta UI rules — the same checks as CI and the PostToolUse hook (class rules + html-attr rules + composition rules for HTML). Use this AFTER generating UI code to self-verify before presenting it. Response always includes coverage info (manual rules cannot be auto-checked).

Input parameters:

- `source` (string, required): Full source code to lint (HTML / JSX / Vue template)
- `sourceType` (string): Source type. "html" (default) also runs composition lint (nested modal etc.); "jsx" runs class + attr lint only

### `search` (~63 tokens)

Search across tokens and components by keyword. Matches against names, values, tailwind classes, and descriptions. Returns up to 20 results (truncated flag when more matched).

Input parameters:

- `query` (string, required): Search keyword (e.g. "card", "primary", "shadow")

### `get_rules` (~97 tokens)

Get melta UI prohibition rules from rules.json (99 total). Use this to retrieve manual/contextual rules that check_rule cannot auto-detect. Supports filtering by category, severity, or detector.

Input parameters:

- `category` (string): Filter by category (e.g. "color", "spacing", "accessibility", "button", "modal")
- `detector` (string): Filter by detector type
- `severity` (string): Filter by severity

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/tsubotax-melta-ui/melta-ds-mcp#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 70
- 2026-08-01: 26
- 2026-07-31: 5
- 2026-07-30: 53
- 2026-07-28: 53
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/melta-ds-mcp
- Socket report: https://socket.dev/npm/package/melta-ds-mcp
- Repository: https://github.com/tsubotax/melta-ui
- Website: https://melta.tsubotax.com/
- Changelog RSS feed: https://verifymcp.io/servers/tsubotax-melta-ui/melta-ds-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/tsubotax-melta-ui/melta-ds-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/tsubotax-melta-ui/melta-ds-mcp