Design

colorfor.ai

Provides color palette and semantic UI theme generation, WCAG contrast checking, and real-world paint matching and quantity estimation tools.

1 endpoint6 known toolsFirst detected September 30, 2026Last detected September 30, 2026

ENDPOINT 1

https://colorfor.ai/api/mcp

No auth detected

MCP server metadata

Name: colorfor.ai
Version: 1.0.0

Capabilities

tools

Server instructions

Deterministic color tools: generate_palette (words → palettes), solve_theme (brand hexes → complete WCAG-verified UI theme), check_contrast (exact WCAG 2.2 ratios), match_paint (hex → closest real RAL paint colors via CIEDE2000), estimate_paint_quantity (room → litres + tin sizes), export_brand_contract (anchors + brand descriptor → four design-system documents from one solve). No LLM invents colors — identical inputs always return identical results.

Known tools 6

generate_palette

Generate 3 deterministic color palette proposals from a plain-language description (e.g.

Inferred read-only

solve_theme

Turn 1-3 brand hex colors into a complete 40-role semantic UI theme (background, surfaces, text tiers, primary/secondary/accent with hover+pressed states, four status colors, borders, focus ring, 8 chart colors) in BOTH light and dark modes, every required pair verified against WCAG 2.2 before it is returned.

Inferred read-only

check_contrast

Exact WCAG 2.2 contrast ratio for a foreground/background hex pair, with pass/fail for AA and AAA at normal and large text sizes.

Inferred read-only

match_paint

Find the closest real-world paint colors (RAL Classic standard) to any hex color, matched with CIEDE2000 — the coatings industry's own color-difference formula.

Inferred read-only

estimate_paint_quantity

Calculate how many litres of paint a room needs and which real tin sizes to buy.

Inferred read-only

export_brand_contract

Emit a complete brand style reference as FOUR documents from a single solve — DESIGN.md (a designer-readable style reference with every colour named, valued, tokenised and explained), tokens.json (DTCG design tokens), variables.css (:root plus a dark block) and theme.css (Tailwind v4 @theme).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.colorfor-ai]
url = "https://colorfor.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "colorfor-ai": {
      "type": "http",
      "url": "https://colorfor.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: colorfor-ai
Remote MCP URL: https://colorfor.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "colorfor-ai": {
      "url": "https://colorfor.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "colorfor-ai": {
      "type": "http",
      "url": "https://colorfor.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "colorfor-ai",
  "transport": "streamable-http",
  "url": "https://colorfor.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for colorfor.ai was fetched 2026-10-01T23:13:05.666Z.

Trust status Neutral

colorfor.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.