Design

standby.design

Generates design tokens (colors, typography, spacing, shapes, icons) for UI systems, compatible with shadcn/ui and supporting light/dark modes.

1 endpoint8 known toolsFirst detected June 30, 2026Last detected September 19, 2026

ENDPOINT 1

https://mcp.standby.design/mcp

No auth detected

MCP server metadata

Name: standby-design
Version: 0.1.6

Capabilities

tools.listChanged

Server instructions

Tools for generating complete design systems with standby.design. Typical flow: generate_color_palette → generate_type_scale → generate_shape_tokens / generate_icon_tokens / generate_space_tokens, passing the returned URL into each subsequent call so the sections accumulate. Every result includes a shareable standby.design/system URL the user can open to view and fine-tune the system visually. Use export_design_system to get the full CSS / Tailwind v4 / W3C design tokens / LLM briefing for a URL, and get_design_system to inspect an existing URL. All tools are pure and deterministic — no network access, no side effects.

Known tools 8

generate_color_palette

Generate a perceptually uniform OKLCH color palette from a brand color: 18-step scales for brand/surface/error/accents, semantic tokens (shadcn/ui compatible), light+dark modes.

Inferred read-only

generate_type_scale

Generate a fluid typographic scale (CSS clamp() between 375px and 1920px viewports) with 11 levels (Display, H1–H6, Body L/M/S, Caption), Fontshare fonts, line heights and letter spacing.

Inferred read-only

generate_shape_tokens

Generate shape tokens — radii, shadows, borders, focus rings — in one of four visual styles: "paper" (classic surfaces with layered shadows), "glass" (liquid glass), "neomorph" (soft neumorphism), "neobrutalism" (hard offset shadows).

Inferred read-only

generate_icon_tokens

Pick an icon set and generate icon sizing tokens (xs–2xl + stroke width).

Inferred read-only

generate_space_tokens

Generate spacing tokens (3xs–3xl), breakpoints, container widths, prose measure, and aspect ratios.

Inferred read-only

get_design_system

Decode a standby.design URL (or raw hash) and return an overview of the full design system: color palette, type scale, spacing & layout, shape tokens, and icons — plus per-tool edit links.

Potential side effects

export_design_system

Generate the full token code for a design system URL in one format: "css" (CSS custom properties incl.

Inferred read-only

list_fonts

List Fontshare font slugs usable in generate_type_scale (headingFont/bodyFont/monoFont), grouped by category.

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.standby-design]
url = "https://mcp.standby.design/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "standby-design": {
      "type": "http",
      "url": "https://mcp.standby.design/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: standby-design
Remote MCP URL: https://mcp.standby.design/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": {
    "standby-design": {
      "url": "https://mcp.standby.design/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "standby-design": {
      "type": "http",
      "url": "https://mcp.standby.design/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "standby-design",
  "transport": "streamable-http",
  "url": "https://mcp.standby.design/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 standby.design was fetched 2026-07-27T09:38:08.837Z and is being refreshed.

Trust status Trusted

standby.design is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

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