PaletteGet

paletteget-mcp

An MCP server for the PaletteGet color palette library: 100 palettes across App, Web and Mini App UIs, each organized into 10 design roles and checked against WCAG contrast requirements.

It exists so your AI coding tool stops inventing hex values. Instead of guessing, the model calls a tool and gets the real role colors, the measured contrast ratios, and the pairing advice that ships with the palette.

No API key, no sign-up.

Use the hosted endpoint (nothing to install)

https://paletteget-mcp.y7206062.workers.dev/mcp

{
  "mcpServers": {
    "paletteget": {
      "type": "http",
      "url": "https://paletteget-mcp.y7206062.workers.dev/mcp"
    }
  }
}

ChatGPT: Settings → Connectors → Add custom connector → paste the URL.

The hosted server embeds the dataset at deploy time, so it never depends on the site being reachable and answers in a few milliseconds.

Or run it locally (stdio)

From npm, no clone

npx -y paletteget-mcp

{
  "mcpServers": {
    "paletteget": {
      "command": "npx",
      "args": ["-y", "paletteget-mcp"]
    }
  }
}

Behind a proxy, set PALETTEGET_PROXY=http://127.0.0.1:7897 in the server's env block.

From source

git clone https://github.com/yang7206/paletteget-mcp.git
cd paletteget-mcp
npm install

{
  "mcpServers": {
    "paletteget": {
      "command": "node",
      "args": ["/absolute/path/to/paletteget-mcp/index.mjs"]
    }
  }
}

The stdio server fetches live data from the public JSON endpoints and caches it for 10 minutes.

Tools

Tool	What it does
list_palettes	List palettes, optionally filtered by platform (app / web / miniapp) or tag
get_palette	Full data for one palette: role colors, contrast results, human-written pairing advice
suggest_palette	Recommend palettes from keywords in English or Chinese, and say what matched
get_css_variables	CSS custom properties for a palette, ready to paste
check_contrast	WCAG contrast between any two colors, with both the body-text and large-text verdicts
suggest_text_color	Readable text colors for a given background: same-hue tints and shades plus black and white, ranked by contrast
darken_palette	Derive a dark-mode version of a light palette with published rules, and the measured contrast of every pair
get_platform_snippet	Paste-ready code for one palette: Android colors.xml, iOS UIColor, Flutter Color, mini program wxss, CSS, SCSS or Tailwind
get_color_scale	Expand one base color into a 50 to 900 scale, with white and black contrast per step; JSON, CSS or Tailwind output

Example call and result:

suggest_palette { "query": "dark finance dashboard", "limit": 2 }

- Ink Blue Night / 墨蓝夜（app，分 94）
  slug: mo-lan-ye　主色: #4c8df6
  场景: Finance & analytics apps (dark mode)
  命中: 标签:dark, 场景:finance

Environment variables (stdio server)

Variable	Default	Purpose
PALETTEGET_API	https://paletteget.com/api/index.json	Override the dataset URL
PALETTEGET_API_ZH	derived (/zh/api/index.json)	Override the Chinese dataset URL
PALETTEGET_CACHE_MS	600000	Cache lifetime in milliseconds
PALETTEGET_PROXY	none	Route requests through a proxy, e.g. http://127.0.0.1:7897. Also honours HTTPS_PROXY.

Behind a firewall, Node's built-in fetch ignores the usual proxy variables, so set PALETTEGET_PROXY explicitly.

Test

npm run smoke

The smoke test speaks the MCP stdio protocol directly and exercises every tool against a local fixture, so it runs offline. Point PALETTEGET_API at the live site to test against production.

Maintaining the hosted worker

The worker (worker.mjs) is a hand-written, stateless subset of MCP Streamable HTTP (initialize, tools/list, tools/call, ping) with no SDK dependency, which keeps it small and Workers-native.

# 1. Regenerate the embedded dataset (run both locales)
SITE_URL=https://paletteget.com SITE_LOCALE=zh node --import ./alias-loader.mjs build-data.mjs
SITE_URL=https://paletteget.com SITE_LOCALE=en node --import ./alias-loader.mjs build-data.mjs

# 2. Local check
npx wrangler dev          # POST JSON-RPC to http://127.0.0.1:8787/mcp

# 3. Deploy (needs CLOUDFLARE_API_TOKEN with Workers Scripts:Edit)
npx wrangler deploy

build-data.mjs reuses the site's own i18n modules through alias-hooks.mjs, so names, scenes and advice stay identical to the published site. data/ is generated at build time and never committed.

Data and license

Code is MIT (see LICENSE). Palette data comes from paletteget.com and may be reused freely in personal and commercial projects; a credit link is appreciated.

Machine-readable forms of the same data, if you would rather skip MCP entirely:

• Full dataset: https://paletteget.com/api/index.json
• One palette: https://paletteget.com/palette-list/{platform}/{slug}/index.json
• CSS variables: https://paletteget.com/palette-list/{platform}/{slug}/index.css
• Agent guide: https://paletteget.com/llms.txt