# ejwhite7/brandkit-mcp [Health: Active]

**Category:** 📐 Architecture & Design  
**Repository:** https://github.com/ejwhite7/brandkit-mcp  
**GitHub Stars:** 5  
**npm Downloads (last month):** 401  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/ejwhite7-brandkit-mcp

## Description
Expose a company's complete design system (colors, typography, logos, components, guidelines, CSS tokens) to AI tools via MCP. Auto-parses CSS / Markdown / PDF / SVG / fonts; supports marketing vs product contexts with shared overrides; ships 12 tools, 16+ resources under brandkit://, and 4 prompts; stdio + SSE + Streamable HTTP transports. Install via NPM: npx -y brandkit-mcp serve.

## Tools
Capabilities this server exposes over MCP:

- **get_brand_overview** — High-level overview of the brand atomic system: brand name, magic_trick presence, inventory counts, contexts, and the full v2 tool list.
- **get_magic_trick** — Return the human-authored magic_trick.md taste primer verbatim. This file is human-write-only — never write to it via any tool.
- **get_positioning** — Return the brand's positioning document (agent/verbal/positioning.md). Includes a taste primer from magic_trick.md.
- **get_audience** — Return the brand's audience definition parsed from agent/verbal/audience.yaml. Freeform YAML; returned as-is. Includes a taste primer.
- **get_messaging** — Return the brand's messaging document (agent/verbal/messaging.md). Includes a taste primer.
- **get_differentiation** — Return the brand's differentiation document (agent/verbal/differentiation.md). Includes a taste primer.
- **get_concepts** — Return the brand's creative concepts/directions (agent/verbal/concepts.md). Includes a taste primer.
- **get_voice** — Return the brand's voice document (agent/verbal/voice.md). Includes a taste primer.
- **get_colors_and_type** — Return colors and typography as CSS custom properties from agent/visual/colors_and_type.css (with optional artifact override).
- **get_assets** — Return logos and other binary assets from agent/visual/assets/. Replaces v1 get_logos + get_textures.
- **get_fonts** — Return font faces declared in agent/visual/fonts/ (binary files + optional fonts.yaml manifest).
- **get_components** — Return UI component specifications from agent/visual/components/. Optionally filtered by context (base | web | product).
- **get_tokens** — Return design tokens from agent/visual/tokens/ specimens. Optional context (base|web|product) and output format (json|css|scss|tailwind|w3c).
- **get_motion** — Return the motion system: parsed motion.json tokens + motion.css text.
- **get_css** — Return raw CSS text from agent/visual/colors_and_type.css and agent/visual/motion/motion.css for the requested context.
- **search_brand** — Full-text search across all brand atomic system content: verbal docs, magic_trick, components, tokens, assets, and CSS files.
- **validate_usage** — Validate that an HTML/CSS snippet uses brand tokens (rather than literal values) and references known components.
- **get_context_diff** — Diff two contexts (base | web | product) across colors_and_type custom properties, components, and tokens.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "brandkit-mcp": {
    "command": "npx",
    "args": ["-y","brandkit-mcp"]
  }
}
```

## Documentation

## What ejwhite7/brandkit-mcp MCP server does

The ejwhite7/brandkit-mcp MCP server makes a brand’s atomic system available as structured MCP tools and resources. It covers verbal identity documents such as positioning, audience, messaging, differentiation, creative concepts, and voice. It also serves visual material including CSS color and typography properties, font files, logos and other assets, component specifications, design tokens, motion definitions, and raw CSS.

The server includes read operations for each major content area, full-text search across indexed brand material, usage validation for HTML and CSS snippets, and context comparisons. A separate local synchronization tool can update `brandkit.config.yaml`, `DESIGN.md`, and `PRODUCT.md`; network transports hide this write-capable operation by default. The human-authored `magic_trick.md` file is returned as a taste primer and is not written by the synchronization tool.

## How it works

A `brandkit.config.yaml` file identifies the brand name, description, root directory, supported contexts, ignored paths, and ingestion limits. Version 2 is required. By default, brand content lives in `brand_atomic_system/`, with verbal files under `agent/verbal/` and visual files under `agent/visual/`.

The server indexes content below the configured brand root while excluding paths such as `human/` when configured. The `human/` area is intended for PDFs and other material that should remain outside the MCP-facing system. File, byte, depth, and count limits bound ingestion, and linked files cannot bypass the root or those limits.

Visual contexts use a shared `base` foundation plus optional `web` and `product` overrides. Verbal content applies globally. Token results can be returned as JSON, CSS, SCSS, Tailwind configuration, or W3C Design Tokens output. The MCP resource catalog uses `brand://` URIs for overview, verbal documents, visual indexes, and motion data.

## Setup and configuration

Install the npm package globally with `npm install -g brandkit-mcp`, then run `brandkit-mcp init` to create a starter brand system. Edit the generated files and connect the server to an MCP client using the `brandkit-mcp serve` command. Claude Desktop configuration uses a server entry with that command and no required credential.

The ejwhite7/brandkit-mcp MCP server expects a version 2 configuration. A typical configuration declares `brand.root`, contexts such as `base`, `web`, and `product`, and optional `ignore` and `ingestion` settings. The initializer refuses to replace an existing configuration or brand directory unless explicitly forced. Version 1 configurations are rejected at startup and require manual migration.

## Tools and capabilities

Available capabilities include:

- Retrieve brand overview data and the human-authored taste primer.
- Read positioning, audience, messaging, differentiation, concepts, and voice documents.
- Return colors, typography, assets, fonts, components, tokens, motion, and raw CSS.
- Search across verbal and visual brand content.
- Validate token and component usage in HTML or CSS snippets.
- Compare base, web, and product visual contexts.
- Expose brand material through MCP resources as well as tools.

The ejwhite7/brandkit-mcp MCP server is suited to website, application, and marketing workflows where generated output must follow an existing brand system rather than inventing its own visual or verbal rules.

_Full upstream README: https://allmcps.com/mcp/ejwhite7-brandkit-mcp/readme_