# Coolors MCP (npm · @trishchuk/coolors-mcp)

Color tools for AI agents: WCAG/APCA contrast, Material 3 HCT themes, palettes, DESIGN.md audits

- Trust score: 69/100 (medium)
- Change this week: +15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `@trishchuk/coolors-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/x51xxx-coolors-mcp/trishchuk-coolors-mcp.md), [page](https://verifymcp.io/servers/x51xxx-coolors-mcp/trishchuk-coolors-mcp)

## Channel facts

- Registry: `npm`
- Package: `@trishchuk/coolors-mcp`
- Version: `2.0.0`
- 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 2026-11-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 45 of 128 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 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3574 tokens (~115/item across 31 items; 31 tools + 0 resources), over budget; trim descriptions and params.
  - 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 31 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **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

### How do I install the Coolors MCP server?

Coolors MCP runs locally as an npm package, launched with npx -y @trishchuk/coolors-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 x51xxx-coolors-mcp -- npx -y @trishchuk/coolors-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "x51xxx-coolors-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@trishchuk/coolors-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "x51xxx-coolors-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@trishchuk/coolors-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add x51xxx-coolors-mcp -- npx -y @trishchuk/coolors-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "x51xxx-coolors-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@trishchuk/coolors-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add x51xxx-coolors-mcp --command npx --arg -y --arg @trishchuk/coolors-mcp
```

### Hermes

```yaml
mcp_servers:
  x51xxx-coolors-mcp:
    command: "npx"
    args: ["-y", "@trishchuk/coolors-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "x51xxx-coolors-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@trishchuk/coolors-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add x51xxx-coolors-mcp -t stdio -c npx -a -y @trishchuk/coolors-mcp
```

### Other

```json
{
  "mcpServers": {
    "x51xxx-coolors-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@trishchuk/coolors-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.

### 2026-11-15 (score 69, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-14 (score 54)

First indexed and scored.

## MCP tools (31)

### `describe_color` (~105 tokens)

Describe what one or more colors actually look like in human perceptual terms (name, warm/cool temperature, lightness & vividness tier, OKLCH/HCT/HSL/RGB values, readable text recommendation, UI role suggestions, and visual pitfalls like bile-zone or halation). Use this whenever you cannot 'see' a hex code.

Input parameters:

- `colors` (array, required): One or more colors to describe (hex, CSS name, rgb, hsl, oklch)

### `fix_contrast` (~190 tokens)

Automatically find the perceptually closest color that meets a WCAG 2.x or APCA contrast target while preserving hue in HCT space. Eliminates trial-and-error guessing.

Input parameters:

- `adjust` (string): Which color to adjust: 'foreground' (default), 'background', or 'auto' (whichever needs smaller ΔE2000)
- `background` (string, required): Background color
- `foreground` (string, required): Foreground/text color
- `prefer` (string): Direction preference for tone adjustment
- `target` (string): Contrast target: 'aa' (4.5:1), 'aaa' (7:1), 'aa-large' (3:1), 'ui' (3:1), 'apca-body' (|Lc|≥75), 'apca-content' (|Lc|≥60), 'apca-large' (|Lc|≥45)

### `design_ui_palette` (~183 tokens)

Design a complete, contrast-verified Light + Dark UI color system from a single brand color following the 60-30-10 rule (60% surfaces/neutrals/text hierarchy, 30% secondary & subtle containers, 10% primary CTA & interactive states + harmonized status colors). Prevents dark-mode neon halation and guarantees WCAG AA/AAA text pairs.

Input parameters:

- `brand` (string, required): Brand seed color (hex, CSS name, rgb, hsl, oklch)
- `format` (string): Output format: markdown report + CSS, css only, json, or W3C tokens
- `harmony` (string): Secondary/accent harmony relative to brand
- `neutralStyle` (string): Neutral tinting: 'tinted' (subtle brand tint, default), 'cool', 'warm', or 'pure' grayscale

### `audit_ui_colors` (~107 tokens)

Audit an entire UI's foreground/background pairs and optional palette swatches in one call. Checks WCAG 2.x, APCA Lc, color-blindness contrast collapses, simultaneous-contrast vibration, and universally disliked colors — and provides exact hue-preserving fixes for every failing pair.

Input parameters:

- `pairs` (array): Foreground/background pairs to audit (up to 100)
- `swatches` (array): Optional standalone palette swatches to check for bile-zone/CVD collisions

### `generate_categorical_palette` (~112 tokens)

Generate N perceptually balanced, color-blind-safe categorical colors for charts, badges, tags, or avatars. Optimizes minimum ΔE2000 across normal vision AND protanopia/deuteranopia/tritanopia so no category vanishes or collides.

Input parameters:

- `background` (string): Target canvas polarity ('light' or 'dark')
- `count` (number, required): Number of distinct categories (2-12)
- `seedColor` (string): Optional brand/anchor color to start the categorical spread from

### `convert_color` (~99 tokens)

Convert colors between formats (hex, rgb, hsl, lab, hct, oklab, oklch). Accepts hex, CSS named colors, rgb(), hsl(), oklch(), oklab(), or hct().

Input parameters:

- `color` (string, required): Color to convert (hex, CSS name, rgb(), hsl(), oklch(), oklab(), or hct())
- `to` (string, required): Target format

### `color_distance` (~69 tokens)

Calculate perceptual distance between two colors using Delta E 2000

Input parameters:

- `color1` (string, required): First color (hex, rgb, or hsl)
- `color2` (string, required): Second color (hex, rgb, or hsl)
- `metric` (string): Distance metric to use

### `check_contrast` (~141 tokens)

Check contrast between two colors using WCAG 2.x luminance ratio, APCA Lc (WCAG 3 draft), or both. Also checks color-blindness contrast drops and suggests an exact hue-preserving fix if contrast fails.

Input parameters:

- `algorithm` (string): Contrast algorithm: 'wcag' (WCAG 2.x ratio), 'apca' (Lc, WCAG 3 draft), or 'both'
- `background` (string, required): Background color
- `foreground` (string, required): Foreground/text color
- `suggestFix` (boolean): Include nearest hue-preserving AA fix and CVD/optical warnings when issues exist

### `adjust_color` (~231 tokens)

Adjust a color using perceptual (oklch, hct) or classic (hsl) math: lighten, darken, saturate, desaturate, hue-shift, tint (mix with white), shade (mix with black), grayscale, invert, or mix with a second color. Perceptual space ('oklch' default) prevents muddy mixes and hue drift.

Input parameters:

- `amount` (number): Amount of change. Percent (0-100) for lighten/darken/saturate/desaturate/tint/shade, degrees (-360..360) for hue-shift, or 0-1 weight of first color for mix. Default 10 / 30 / 0.5.
- `color` (string, required): Color to adjust (hex, CSS name, rgb, hsl, oklch)
- `operation` (string, required): Adjustment operation
- `space` (string): Color space for adjustment: 'oklch' (default, perceptually uniform), 'hct', or 'hsl'
- `with` (string): Second color (only for mix)

### `generate_palette` (~202 tokens)

Generate a color palette using color theory harmonies (monochromatic, analogous, complementary, split-complementary, triadic, tetradic, square, compound, shades-and-tints). Defaults to perceptual HCT space, avoids universally disliked colors, and describes each swatch so agents can see what was generated.

Input parameters:

- `allowDisliked` (boolean): Allow dark yellow-green 'bile zone' colors (default false)
- `baseColor` (string, required): Base color for palette generation
- `count` (number): Number of colors to generate
- `includeDetails` (boolean): Include perceptual name, temperature, tone, and best text ink for each swatch
- `space` (string): Wheel space: 'hct' (perceptual default), 'oklch' (CSS perceptual), 'ryb' (painter's red-yellow-blue wheel), or 'hsl'
- `type` (string): Type of color harmony

### `generate_palette_with_locks` (~126 tokens)

Generate a color palette while preserving specific locked colors. Uses deterministic perceptual search in OKLCH/HCT/LAB/HSL and avoids universally disliked colors.

Input parameters:

- `colorSpace` (string): Color space for palette generation/interpolation (oklch/hct/lab are perceptually uniform)
- `lockedColors` (array, required): Colors that must be included in the palette
- `mode` (string): Generation mode: harmony (cohesive), contrast (distinct), or gradient (smooth transition)
- `totalColors` (number, required): Total number of colors in the final palette

### `generate_gradient` (~135 tokens)

Generate a smooth gradient between colors with multiple interpolation methods (oklch, oklab, lab, lch, hct, hsl, rgb)

Input parameters:

- `colors` (array, required): Colors to create gradient between (2-32)
- `easing` (string): Easing function for gradient transition
- `format` (string): Output format for the gradient
- `interpolation` (string): Color space for interpolation (oklch/oklab/lab/lch/hct are perceptually smooth)
- `steps` (number, required): Total number of colors in the gradient, including every input color (must be ≥ number of colors)

### `export_palette` (~155 tokens)

Export a list of colors as CSS custom properties, SCSS variables, a Tailwind config snippet, W3C design tokens, JSON, or a DESIGN.md `colors:` block.

Input parameters:

- `colors` (array, required): Palette colors (up to 256)
- `format` (string, required): Output format: css (custom properties), scss (variables), tailwind (config), tokens (W3C design tokens), json, design-md (DESIGN.md `colors:` YAML for the front matter)
- `names` (array): Optional names for each color. Length must match colors. Defaults to a 50/100…900 scale.
- `prefix` (string): Optional prefix for variable/token names (e.g. 'brand')

### `simulate_color_blindness` (~105 tokens)

Simulate how one or more colors appear to viewers with color vision deficiency (protanopia, deuteranopia, tritanopia, their milder anomaly forms, or achromatopsia).

Input parameters:

- `colors` (array, required): Colors to simulate (hex, rgb, hsl), up to 64
- `types` (array): Deficiency types to simulate. Defaults to all 7 (dichromacy + anomaly + achromatopsia).

### `check_palette_accessibility` (~113 tokens)

Audit a color palette for color-blind accessibility. For each pair of colors, reports the perceptual distance (Delta E 2000) under each CVD type and flags pairs that become indistinguishable.

Input parameters:

- `colors` (array, required): Palette colors to audit (2-64)
- `indistinguishableThreshold` (number): ΔE2000 below which two simulated colors are considered indistinguishable (default 10)
- `types` (array): CVD types to audit. Defaults to all 7.

### `generate_tonal_scale` (~148 tokens)

Generate a complete tonal scale (Tailwind-style 50/100/.../900/950) from a seed color. Uses Google's HCT color space so each step is perceptually even — ideal for building shadable design-system colors.

Input parameters:

- `chromaBoost` (number): Multiplier on seed chroma (1 = preserve, <1 = muted)
- `name` (string): CSS variable base name (default: 'color')
- `seed` (string, required): Seed color (hex, rgb, hsl)
- `stops` (array): Custom stops. Default: [50,100,200,300,400,500,600,700,800,900,950].

### `generate_state_colors` (~97 tokens)

Generate consistent interaction-state colors (hover / active / pressed / focus / disabled / selected) from a base color. Steps are computed in HCT space so they keep equal perceptual weight regardless of base hue.

Input parameters:

- `base` (string, required): Base/resting color (hex, rgb, hsl)
- `isDark` (boolean): Whether the base color sits on a dark background. Hover lightens on dark, darkens on light.

### `analyze_palette_consistency` (~64 tokens)

Score how visually cohesive a palette is. Reports tonal step uniformity, chroma spread, hue distribution, and a single 0-100 cohesion score, plus targeted suggestions for tightening it up.

Input parameters:

- `colors` (array, required): Palette colors to analyze (2-64)

### `generate_semantic_palette` (~96 tokens)

From a single brand color, generate a complete visually-cohesive semantic palette: primary, secondary, tertiary, plus success/warning/error/info status colors. Tone and chroma are normalized in HCT space so every color feels like part of the same family.

Input parameters:

- `brand` (string, required): Brand / seed color (hex, rgb, hsl)
- `isDark` (boolean): Generate the palette for a dark theme background

### `generate_material_theme` (~49 tokens)

Generate a complete Material Design 3 color theme from a source color

Input parameters:

- `includeCustomColors` (boolean): Include custom color palettes
- `sourceColor` (string, required): Source color for theme generation

### `harmonize_colors` (~58 tokens)

Harmonize colors to work better together using Material Design algorithms

Input parameters:

- `colors` (array, required): Array of colors to harmonize
- `factor` (number): Harmonization strength (0-1)
- `method` (string): Harmonization method

### `generate_tonal_palette` (~51 tokens)

Generate a Material Design tonal palette from a color

Input parameters:

- `color` (string, required): Base color for palette
- `tones` (array): Custom tone values 0-100 (default: Material standard tones)

### `match_theme_color` (~76 tokens)

Find the closest matching theme variable for a given color

Input parameters:

- `color` (string, required): Color to match (hex, rgb, hsl)
- `context` (string): Usage context for better matching
- `minConfidence` (number): Minimum confidence threshold (0-100)
- `themeCSS` (string, required): CSS containing theme variables

### `refactor_css_with_theme` (~86 tokens)

Refactor CSS to use theme variables instead of hardcoded colors

Input parameters:

- `css` (string, required): CSS content to refactor
- `generateReport` (boolean): Generate detailed refactoring report
- `minConfidence` (number): Minimum confidence for replacements
- `preserveOriginal` (boolean): Keep original values as comments
- `themeCSS` (string, required): CSS containing theme variables

### `match_theme_colors_batch` (~55 tokens)

Find theme matches for multiple colors at once

Input parameters:

- `colors` (array, required): Array of colors to match
- `context` (string): Usage context for all colors
- `themeCSS` (string, required): CSS containing theme variables

### `generate_theme_css` (~101 tokens)

Generate CSS custom properties for a complete theme from a source color

Input parameters:

- `includeTones` (array): Tone values to include (default: 0,10,20,30,40,50,60,70,80,90,95,99,100)
- `prefix` (string): Prefix for CSS variables (e.g., 'color' → --color-primary-50)
- `sourceColor` (string, required): Source color for theme generation

### `extract_image_colors` (~87 tokens)

Extract dominant colors from an image. Input should be image data as an array of RGBA values.

Input parameters:

- `format` (string): Output format
- `imageData` (object, required): Image data with RGBA values (at most 65536 pixels; downscale larger images)
- `maxColors` (integer): Maximum number of colors to extract
- `quality` (string): Extraction quality

### `generate_theme_from_image` (~78 tokens)

Generate a complete Material Design 3 theme from an image

Input parameters:

- `imageData` (object, required): Image data with RGBA values (at most 65536 pixels; downscale larger images)
- `includeCustomColors` (boolean): Include custom colors from image
- `isDark` (boolean): Generate dark theme (false for light theme)

### `audit_design_md` (~210 tokens)

Audit the color tokens of a DESIGN.md file (Google Labs design-system format: YAML front matter / ```yaml blocks with `colors` and `components`). Checks WCAG + APCA contrast for pairs declared in components (backgroundColor/textColor) and pairs inferred from token names (on-X ↔ X, text ↔ surface), color-blind collisions between accent/status colors, exact and near-duplicate tokens, disliked colors, broken {colors.x} references and a missing `primary`. Suggests same-hue fixes for failing pairs. Pass the file's full text.

Input parameters:

- `cvdThreshold` (number): ΔE2000 below which two accent/status colors count as indistinguishable under color-vision deficiency
- `designMd` (string, required): Full text of the DESIGN.md file
- `maxItems` (integer): Maximum rows listed per report section
- `textThreshold` (number): Minimum WCAG contrast for text pairs (4.5 = AA normal text, 7 = AAA)

### `analyze_color_likability` (~68 tokens)

Check if a color is universally disliked (dark yellow-green associated with biological waste) and get a fixed version if needed

Input parameters:

- `autoFix` (boolean): Automatically return fixed version if disliked
- `color` (string, required): Color to analyze (hex, rgb, hsl, etc.)

### `fix_disliked_colors_batch` (~62 tokens)

Analyze and fix multiple colors, returning only liked versions

Input parameters:

- `colors` (array, required): Array of colors to analyze (hex, rgb, hsl, etc.), up to 100
- `includeAnalysis` (boolean): Include detailed analysis for each color

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/x51xxx-coolors-mcp/trishchuk-coolors-mcp#diagnostics

## Score history

- 2026-11-21: 69
- 2026-11-20: 69
- 2026-11-19: 69
- 2026-11-18: 69
- 2026-11-17: 69
- 2026-11-16: 69
- 2026-11-15: 69
- 2026-11-14: 54

## Common questions

### What is the Coolors MCP server?

Coolors MCP is listed in the public MCP registry as io.github.x51xxx/coolors-mcp. Color tools for AI agents: WCAG/APCA contrast, Material 3 HCT themes, palettes, DESIGN.md audits. This page covers its npm package (@trishchuk/coolors-mcp).

### Is the Coolors MCP server safe to use?

Coolors MCP scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 Coolors MCP server expose?

Coolors MCP exposes 31 tools: describe_color, fix_contrast, design_ui_palette, audit_ui_colors, generate_categorical_palette, and 26 more. Their descriptions and schemas cost roughly 3,459 tokens of context every time the server is loaded.

### Is the Coolors MCP server still maintained?

Coolors MCP is still listed as active in the MCP registry. We last reached this channel on 21 November 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 Coolors MCP server under?

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

### What did VerifyMCP test on the Coolors MCP server?

VerifyMCP ran 15 checks on Coolors MCP, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Coolors MCP: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@trishchuk/coolors-mcp
- Socket report: https://socket.dev/npm/package/@trishchuk/coolors-mcp
- Repository: https://github.com/x51xxx/coolors-mcp
- Website: https://x51xxx.github.io/coolors-mcp/
- Changelog RSS feed: https://verifymcp.io/servers/x51xxx-coolors-mcp/trishchuk-coolors-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/x51xxx-coolors-mcp/trishchuk-coolors-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/x51xxx-coolors-mcp/trishchuk-coolors-mcp.json
- HTML version of this page: https://verifymcp.io/servers/x51xxx-coolors-mcp/trishchuk-coolors-mcp
