Skip to main content
Glama
Colors MCP Server

Colors MCP Server

by HtetOoWaiYan

Build a palette

colors_palette
Read-onlyIdempotent

Generate finished color palettes in hex: tonal ramps, light/dark UI themes with contrast checks, color-blind-safe categorical sets, and symmetric diverging scales.

Instructions

Build a finished color palette with verified accessibility. kind "ramp": an 11-step tonal scale of a color (lightest to darkest, the seed is one step, evenly spaced). kind "theme": light and dark UI tokens (background, surface, surface-raised, text, text-muted, border, primary, on-primary) from a brand color, with every text contrast rule checked. kind "categorical": N clearly different, color-blind-safe colors for charts. kind "diverging": a scale from color through a light neutral to color2, with symmetric lightness. Returns hex values ready to use.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>"
    },
    "name": "colors_palette"
  }
}

Input Schema

NameRequiredDescriptionDefault
cvdNoCategorical only: color-blindness types the set must survive. Default "all" (protan, deutan, tritan).all
kindYes"ramp" = tonal scale (50..950) of one color; "theme" = light + dark UI tokens from a brand color; "categorical" = a set of clearly different colors for charts or tags; "diverging" = a scale from one color through a light neutral to a second color.
colorNoSeed color. Required for "ramp" and "theme" (the brand color) and for "diverging" (the left end). Ignored for "categorical".
countNoCategorical only: how many colors. Default 5.
stepsNoRamp: number of steps, default 11 (named 50, 100 ... 950). Diverging: an odd number of steps, default 7.
color2No"diverging" only: the color at the right end.
backgroundNoCategorical only: the background the colors sit on. Default "#ffffff".#ffffff

Output Schema

NameRequiredDescriptionDefault
kindYes
namesNo
themeNo
colorsNo
seedIndexNo
separationNo
contrastRulesTotalNo
contrastRulesPassedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.1.0

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, closed-world, non-destructive, so the bar is low. The description still adds real generation semantics beyond the annotations: even step spacing with the seed occupying one step, symmetric lightness on diverging scales, contrast rules checked on every theme token, and color-blind survival for categorical sets. It does not disclose ordering guarantees beyond "lightest to darkest" or failure behavior for a missing/invalid seed color.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and output guarantee are front-loaded, then one clause per mode — structurally strong and scannable. There is notable redundancy: the four kind definitions largely restate the schema's kind enum descriptions nearly verbatim, so a chunk of the text is not adding new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation, and the description notes hex output anyway. Seven parameters at 100% coverage plus conditional requirements (seed needed for ramp/theme/diverging) are covered. The remaining gap is competitive guidance against the palette-adjacent siblings, which the description never addresses.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description earns the extra point by explaining mechanics the schema only hints at — that the seed is one of the ramp steps and that the ramp is evenly spaced, and that diverging runs color → light neutral → color2. It does not add anything for cvd, count, background, or steps beyond what the enum/int descriptions already say.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and artifact ("Build a finished color palette with verified accessibility") and then enumerates four distinct modes with the exact output of each (11-step tonal scale, light/dark UI tokens, N color-blind-safe chart colors, symmetric diverging scale). An agent can tell this is the palette *generator*, distinct from adjust/audit/convert siblings, without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the mode breakdown — you pick "theme" when you need UI tokens with checked text contrast, "categorical" for chart series — which is decent in-tool routing. But there is no explicit statement of when to use this versus siblings like colors_harmony or colors_audit, and no exclusions or prerequisites (e.g. that a seed color is mandatory for ramp/theme).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.