BrandKit MCP
The BrandKit MCP server exposes a complete brand design system to AI tools via MCP, enabling structured retrieval, search, comparison, and validation of brand identity assets and guidelines.
Verbal Identity
Retrieve brand positioning, audience, messaging, differentiation, creative concepts, and brand voice/tone documentation.
Access a human-authored taste primer (
magic_trick.md) injected into creative tools.
Visual Identity
Colors – Full palette with hex/RGB values, semantic roles, and usage guidelines; output as JSON, CSS, SCSS, Tailwind, or W3C Design Tokens.
Typography – Font families, sizes, weights, line heights, and usage guidelines per context.
Logos – Variants (primary, mark, wordmark, monochrome) with usage rules, clear space, minimum sizes, and optional base64 image data.
Components – UI component specs, variants, CSS properties, and usage guidelines, filterable by name, context, or category.
Design Tokens – Export in CSS custom properties, SCSS variables, Tailwind config, W3C Design Tokens, or JSON.
Textures & Patterns – Texture/pattern assets with usage context and optional base64 data.
Raw CSS – Raw CSS file contents and extracted custom property definitions.
Cross-Cutting Tools
Full-Text Search – Search across all brand content: guidelines, component specs, color names, typography, and documentation.
Context-Specific Data – Query elements by context (base, web/marketing, product) with artifact overrides.
Context Diff – Compare design contexts (e.g., marketing vs. product) side-by-side, highlighting differences in colors, typography, and components.
Brand Compliance Validation – Validate specific color, font, or logo usages against brand guidelines, returning pass/fail with guidance.
Resource URIs – Access brand assets and documents directly via
brand://URIs across 18 tools and 14 MCP resources.
BrandKit MCP
Give every AI tool access to your company's complete brand atomic system via the Model Context Protocol.
BrandKit MCP v2 is an open-source MCP server that exposes a company's complete brand atomic system -- verbal identity (positioning, audience, messaging, differentiation, concepts, voice) and visual identity (colors, typography, components, tokens, motion, assets) -- to Claude and other AI tools via the Model Context Protocol (MCP). It ships 18 tools and 14 resources. When an LLM helps build a website, app, or marketing asset, it has instant structured access to the exact brand language and visual rules it needs -- including a human-authored taste primer that carries the brand's instincts, not just its specs.
Quick Start
# 1. Install
npm install -g brandkit-mcp
# 2. Scaffold a new brand atomic system from the starter template
brandkit-mcp init
# 3. Edit the scaffolded files with your brand content
# 4. Wire into Claude Desktop (or any MCP-compatible client)
# Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
# {
# "mcpServers": {
# "brandkit": {
# "command": "brandkit-mcp",
# "args": ["serve"]
# }
# }
# }Repository Structure
A brand atomic system lives under a single <brand-root>/ directory (default: ./brand_atomic_system):
<brand-root>/
├── readme.md
├── magic_trick.md # human-authored taste primer
├── brandkit.config.yaml # version: 2
├── human/ # PDFs and human-only material (MCP ignores)
│ └── *.pdf
└── agent/
├── verbal/
│ ├── positioning.md
│ ├── audience.yaml
│ ├── messaging.md
│ ├── differentiation.md
│ ├── concepts.md
│ └── voice.md
└── visual/
├── colors_and_type.css
├── fonts/
├── assets/
├── components/
├── tokens/
├── motion/
│ ├── motion.json
│ └── motion.css
└── artifacts/
├── web/ # override layer
└── product/ # override layerThe human/ directory is intentionally ignored by the MCP server -- put PDFs, print specs, or any other human-only material there. Everything under agent/ is indexed and served.
MCP Tools Reference
BrandKit MCP exposes 18 tools to AI assistants:
Tool | Description |
| High-level overview + taste primer |
| Verbatim magic_trick.md |
| Positioning document |
| Audience YAML, parsed |
| Messaging document |
| Differentiation document |
| Creative concepts/directions |
| Voice document |
| Colors + typography custom properties |
| Logos + brand assets |
| Font faces |
| UI primitives |
| Token specimens |
| Motion system (json + css) |
| colors_and_type.css + motion.css text |
| Full-text search |
| Validate brand compliance |
| Diff base vs web vs product |
Taste primer
Seven creative/verbal tools (get_brand_overview, get_positioning, get_audience, get_messaging, get_differentiation, get_concepts, get_voice) inject a _taste_primer field carrying magic_trick.md verbatim. get_magic_trick returns the primer directly without wrapping.
MCP Resources
BrandKit MCP exposes 14 brand:// URIs as MCP resources:
URI | Description |
| Brand overview |
| Taste primer |
| Positioning document |
| Audience YAML |
| Messaging document |
| Differentiation document |
| Creative concepts |
| Voice document |
| Colors + typography CSS |
| Asset index |
| Font face index |
| Component index |
| Token specimens |
| Motion system |
Configuration
The brandkit.config.yaml file at your project root controls BrandKit MCP:
version: 2
brand:
name: Acme Corp
description: Plumbing for builders.
root: ./brand_atomic_system
contexts: [base, web, product]
ignore:
- human/version: 2 is required. A config file missing this field or declaring version: 1 causes the server to throw BrandkitV1ConfigError at startup.
Context System
BrandKit v2 supports three contexts:
Context | Purpose |
| Shared foundation -- fonts, core colors, global tokens |
| Overrides for the public-facing website ( |
| Overrides for the SaaS application ( |
Verbal content (agent/verbal/) has no context overrides -- it applies globally. Visual content can be overridden per context via the artifacts/ layer.
Migrating from v1
2.0.0 is a breaking release. The directory layout, context vocabulary, and tool surface have all changed. No automated migration is included -- the path mapping is manual:
v1 path | v2 path |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Your brandkit.config.yaml must also be updated to declare version: 2 and use the new brand.root field. v1 configs throw BrandkitV1ConfigError at startup -- the server will not start until the config is updated.
Conventions
magic_trick.md is human-authored. The MCP reads it but no tool writes to it. If write tools are added in a future version, they must denylist this path. The taste primer is the brand's instincts -- it must stay human.
Token output formats. The get_tokens tool supports CSS custom properties, SCSS variables, Tailwind config, W3C Design Tokens, and flat JSON.
Transports. The server supports stdio (recommended for Claude Desktop), SSE (legacy HTTP), and Streamable HTTP (current MCP spec).
CLI Reference
brandkit-mcp <command> [options]
Commands:
init [directory] Scaffold a brand atomic system from the starter template
validate [config] Validate configuration and scan for issues
serve Start the MCP server
preview Start the local preview server
docs Generate project documentation files
Global Options:
--version Show version number
--help Show helpContributing
Contributions are welcome.
git clone https://github.com/ejwhite7/brandkit-mcp
cd brandkit-mcp
npm install
npm run build
npm testTypeScript strict mode
ESM imports with
.jsextensionsNo
anytypes -- use proper interfacesTests use Vitest
License
MIT -- see LICENSE for details.
Built with the Model Context Protocol by Anthropic.
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ejwhite7/brandkit-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server