CSS Crème

com.csscremePublished by csscreme.comOfficial publisherv1.8.1Updated Oct 26, 2026

Give your agent a real design system: tokens, measured WCAG contrast, and rules to follow.

VerifiedStreamable HTTPWeb executableDeveloper ToolsMedia & Design

Overview

AI-generated overview

Gives a coding agent curated design systems as DESIGN.md files: tokens, measured WCAG contrast and rules, plus tools to decode live sites' CSS.

What you can do
  • Search and browse curated themes and templates, then fetch a theme's DESIGN.md with semantic colour roles, shadcn tokens, typography, spacing and measured contrast ratios
  • Get paste-ready shadcn/ui registry tokens and CSS variables, plus the exact install command for a theme
  • Get guidance on where DESIGN.md belongs for a given coding agent and a standing-instructions block to paste into agent rule files
  • Decode a public site's HTML and stylesheets into tokens, colours, fonts, radii, spacing and a full DESIGN.md, or sample several pages to see what is consistent
  • Check a DESIGN.md fingerprint against the current token set and report whether a copy is stale
  • Look up a modern CSS feature's…
When to use it
Useful when an assistant is asked to build or restyle UI and needs a concrete, checkable design system instead of inventing a palette, or when you want to extract the design language of an existing site and hold generated UI to it.
Requirements
Remote MCP endpoint over streamable HTTP; no account, API key or paid tier is required. The URL-decoding tools need network access to the public sites being read.
Before you install
The URL tools fetch public sites' HTML and stylesheets, so the addresses you pass are sent to the server. Installing a theme runs an npx shadcn command that writes files into your project. Generated DESIGN.md files should be verified against their fingerprint so stale tokens are not followed.

Installation

In SourceWeft

  1. Open CSS Crème in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.csscreme%2Fdesign-systems/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "css-cr-me": {
      "type": "http",
      "url": "https://csscreme.com/mcp"
    }
  }
}

README

csscreme skill

A Claude Code skill that gives a coding agent a real design system before it writes UI: semantic tokens, measured WCAG contrast, and rules it can be held to.

Free. No account, no API key, no paid tier.

Why

An agent asked for UI with no design system does the same thing every time: invents a palette, mixes three or four corner radii, adds a second font nobody asked for, and ships contrast that was never checked. The result is recognisable on sight, and no amount of prompt rewording fixes it, because the problem is missing input rather than weak instruction.

A file fixes it. Tokens the agent must use, ratios that were computed rather than asserted, and numbered rules that can be diffed against what actually got built. "Use only these six roles" is checkable. "Make it clean" is not.

Install

Fastest: connect the MCP server (free, no account, no key):

bash
claude mcp add --transport http csscreme https://csscreme.com/mcp

That gives the agent thirteen tools with no files to manage: search_themes, list_themes, get_design_md, get_theme_tokens, get_install_command, get_agent_rules, how_to_use, decode_url, get_design_md_for_url, decode_site, verify_design_md, css_feature and get_scene_embed. The URL tools are the ones worth knowing about: point the agent at a live URL and it decodes that site into the same format, then checks its own generated UI against the file afterwards. css_feature answers whether a modern CSS feature is safe to ship, from Baseline data and from what curated sites actually ship. The skill below adds the house rules on top.

As a skill

Claude Code (project):

bash
mkdir -p .claude/skills/csscremecurl -o .claude/skills/csscreme/SKILL.md \  https://raw.githubusercontent.com/damnepic/csscreme-skill/main/SKILL.md

Claude Code (all projects): same, into ~/.claude/skills/csscreme/.

Then ask for UI as normal. The skill fires on things like "build a dashboard", "make this look less generic", or "match the design of stripe.com".

What it does

  1. Fetches a DESIGN.md for one of the curated themes at https://csscreme.com/themes.
  2. Or extracts one from any site via https://csscreme.com/extract - URL or screenshot in, role-mapped tokens out, contrast checked in both modes.
  3. Installs the tokens for real with npx shadcn@latest add <registry-url>.

Endpoints it uses

URLReturns
csscreme.com/d/<slug>.mdDESIGN.md for a curated theme
csscreme.com/d/t/<slug>.mdDESIGN.md for a template theme
csscreme.com/t/<id>.mdDESIGN.md for an extracted theme
csscreme.com/r/<slug>.jsonshadcn/ui registry item
csscreme.com/t/<id>.jsonshadcn/ui registry item, extracted
csscreme.com/mcpMCP server (JSON-RPC 2.0 over POST)

All CORS-open and cacheable, served as text/markdown or application/json.

What the agent actually gets

A DESIGN.md is a contract rather than a description. Eight fields: semantic colour roles in hex and OKLCH, the full shadcn token set in light and dark, two font families, one radius token, an explicit spacing scale, WCAG contrast ratios that were computed rather than asserted, numbered rules each checkable against the tables above them, and paste-ready CSS variables.

The contrast section is the part worth reading twice. If a colour pair fails AA, the file says FAILS WCAG instead of quietly shipping it. Nothing in the file is an adjective the agent has to interpret.

Works with other tools too

The files are plain Markdown, so nothing here is Claude-specific. Per-tool wiring for Cursor, Codex, v0 and Lovable: https://csscreme.com/ai/design-md

The format

Full field spec, with a worked example generated at build time: https://csscreme.com/ai/design-md

Nobody owns the DESIGN.md file name, us included. The useful part here is the generator and the measured contrast, not the noun.

Licence

MIT. The skill is MIT; the themes it fetches are free to use.

Source: README.md at commit 7cee22b

Tools

13

search_themes

Search design systems

Find a design system by describing what you are building ("dark developer tool", "calm fintech dashboard", "playful consumer app"). Returns matching themes with their DESIGN.md URL and shadcn install command. Call this first when the user has no design system defined.

Parameterskindmodelimitqueryrequired

list_themes

List all design systems

Browse the full catalogue of curated themes and templates. Use when the user wants to see options rather than search for one.

Parameterskindmode

get_design_md

Get a DESIGN.md

Fetch the full DESIGN.md for one theme: semantic colour roles, the complete shadcn token set in light and dark, typography, radius, spacing, MEASURED WCAG contrast ratios, and numbered rules the generated UI must follow. Read this before writing any UI. Save it at the repo root as DESIGN.md so it applies to every session.

Parametersidrequired

get_theme_tokens

Get raw theme tokens

Get the shadcn/ui registry item (OKLCH tokens, light and dark) plus the paste-ready CSS variables for one theme, and the one-line command that installs it for real. Use after get_design_md when you are ready to write the tokens into globals.css.

Parametersidrequiredformat

how_to_use

How to wire a DESIGN.md into this tool

Explains where a DESIGN.md belongs for a given coding agent (Claude Code, Cursor, v0, Codex, Lovable) so the design rules apply to every session rather than one message.

Parameterstool

get_install_command

Get the one-line install command

Return the exact `npx shadcn@latest add <url>` command that installs one theme into a shadcn/ui project, plus the registry URL it reads. Use when the user says "install it" and you already know the id.

Parametersidrequired

get_agent_rules

Get a rules block for CLAUDE.md / AGENTS.md / .cursor/rules

Return a short standing-instructions block that makes every future session read DESIGN.md before touching UI. Paste it whole into CLAUDE.md, AGENTS.md or .cursor/rules/design.mdc. It points at the DESIGN.md rather than restating it, and carries the token fingerprint so drift is detectable.

Parametersidrequired

decode_url

Decode any live site into design tokens

Fetch a public site's HTML and stylesheets and return what its CSS declares: named custom properties that look like design tokens, the colours it uses most, its font stacks, border radii, spacing values, and the framework it appears to be built with. Also returns a "drop" report: roughly how many words a web-to-markdown reader would carry away from this page, against the design decisions it would discard, because markdown is defined by throwing the design layer away. It reads CSS and does not render the page, so it reports a confidence ("tokens" when named properties were found, "derived" when only compiled CSS was available) and flags a JavaScript shell rather than pretending every site is equally legible. It obeys the site's robots.txt for CSSCremeBot: a disallowed path is refused with ROBOTS_DENIED, which a retry will not change. A bot challenge, a parked or for-sale domain, or a host's default page is refused with NOT_THE_SITE and the evidence, rather than measured as if it were the site. Every error starts with its code and a retry verdict (never, later, with-changes). A read is reused for up to maxAge seconds (default 600, 0 for fresh), and every result carries `work`: the requests it made of the site. Use when the user wants to match a site that is not in the catalogue, or has fetched a page as markdown and needs what that markdown lost.

ParametersurlrequiredexpectformatmaxAgeexpectSpec

css_feature

Is this CSS feature safe to ship, and who ships it

Answers two questions about a modern CSS feature with data instead of recall. First, its Baseline status (widely available, newly available, or limited availability), the date, and which core browsers lack it, read from the open web-features dataset at build time. Second, how many of CSS Crème's curated, decoded showcase sites ship it, which ones, how many of them guard it with @supports, and the exact @supports conditions they test. Also returns a fallback note where we have one, any name the feature has shipped under before (an agent that learned the old name will otherwise write it), and the documented limits that catch people out, each cited to the page it was read on. Call it before writing CSS that uses container queries, :has(), anchor positioning, @scope, view transitions, oklch(), color-mix(), light-dark(), subgrid, scroll-driven animations, @property, text-wrap and similar, so the CSS you write is accurate for today rather than for your training date. With no feature given it returns the Ship Gap: features that are safe and mostly ignored, and features that are early and shipped anyway.

Parametersfeature

get_design_md_for_url

Get a complete DESIGN.md for any public URL

Read the stylesheets of a public site and return a full DESIGN.md: semantic roles with the token each came from, measured WCAG contrast pairs, the tokens the site itself declares (framework internals counted separately), font families, the type scale with the ratio between steps, colour frequency, gradients, corner radii, spacing, an elevation ladder of shadows, breakpoints, the z-index ladder, interaction-state rule counts, motion, and whether a dark theme is declared. This is the artefact to hand a coding agent before it writes UI that should match a site. It reads declared CSS and does not execute JavaScript, so it reports what the stylesheets say rather than what the page renders.

ParametersurlrequiredmaxAge

decode_site

Measure a design system across a whole site, not one page

Read a sample of pages from one site (from its sitemap.xml, or the homepage links when there is no sitemap) and report what is CONSISTENT across them: which declared tokens, colours, font stacks, radii and spacing values appear on every page read, and which appear on only some. One page shows what a page uses; a design system is a claim about consistency, and only a sample can test it. Returns counts and the pages actually read, never a score. Use when the user asks whether a site is really on a system, or wants the system rather than one page of it.

ParametersurlrequiredpagesmaxAge

verify_design_md

Check whether a DESIGN.md copy is still current

Every DESIGN.md carries a Fingerprint line. Pass the id and that fingerprint; the server answers whether the copy matches the current token set, and if not, returns the current tokens so the agent can update the file instead of following a stale one. Call this at the start of a session when a DESIGN.md is already in the repo.

Parametersidrequiredfingerprintrequired

get_scene_embed

Embed code for a living 3D scene, in a brand's colours

Returns paste-ready code for a CSS Crème Scene: an interactive 3D meadow (four seasons, dandelion clocks, or a garden of peonies, white roses, lilies, irises, hydrangeas, tulips or daffodils, at any hour) grown by code in the browser, with no models or images to load. Give it the `roles` (and optionally `colors`) from a decode_url result and the three flowers take that site's declared colours, each with its source named; or pass a `palette` of hex values. It reads no URL itself. Returns the <creme-scene> element, an iframe, a full-screen link and the licence line. Free to embed with the visible credit.

Parametersmodetimerolescolorsseasonpalette

Version history

4
  1. v1.8.1LatestSep 26, 2026
  2. v1.6.1Sep 19, 2026
  3. v1.6.0Sep 19, 2026
  4. v1.5.0Sep 19, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts