mcpField
H
housestyle

housestyle

Local
github.com/myanptlDeveloper Tools0Updated 6d ago
Repository

About housestyle

housestyle is an MCP server for auditing and improving CSS design choices in AI-built interfaces. It identifies common visual patterns and provides tools for font selection, contrast checks, color palettes, and fluid type scales.

Key features

  1. 01Audit CSS for generic design patterns
  2. 02Suggest fonts and cross-category pairings
  3. 03Check WCAG and APCA contrast
  4. 04Build an 11-step OKLCH color ramp
  5. 05Generate fluid modular type scales

Use cases

  1. 01Review an AI-built interface stylesheet
  2. 02Choose fonts for a role and visual mood
  3. 03Evaluate text contrast for dark themes
  4. 04Create color and typography tokens

MCP support

Exposes CSS auditing and design utilities as tools for MCP clients, including font suggestions, contrast checks, palette generation, and type-scale construction.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "myanptl-housestyle": {
      "command": "npx",
      "args": [
        "-y",
        "housestyle-mcp"
      ]
    }
  }
}
Run commandnpx -y housestyle-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmhousestyle-mcp1.0.2

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
cssstringYesStylesheet text, a design-token block, or a Tailwind config. Paste the real thing rather than a summary.

Details

From the project README

housestyle-mcp

Spots CSS that looks AI-made and suggests fixes for fonts, colour and contrast.

claude mcp add housestyle -- npx -y housestyle-mcp

MIT licence.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.