BrandKit MCP
ejwhite7/brandkit-mcp
Acesso nativo da IA ao sistema de design completo da sua empresa
Ver no GitHubServidor MCP open-source que expõe o sistema atômico de marca de uma empresa (identidade verbal e visual) para Claude e outras ferramentas de IA via Model Context Protocol. Inclui 18 ferramentas e 14 recursos para acesso estruturado a posicionamento, voz, paleta de cores, tipografia, componentes e tokens de design.
Instalação
npx convez-ai ejwhite7/brandkit-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Gerar assets de marketing alinhados com brand guidelines
- Construir websites e apps mantendo identidade visual consistente
- Criar conteúdo com voice e messaging padronizados
- Acelerar handoff de design para desenvolvimento
Veredito

Solução prática para governança de marca em fluxos de IA. Bem estruturada, com CLI acessível e integração direta com Claude. Recomendado para times que precisam escalar produção criativa sem drift de identidade.
README
A tradução para o português deste README ainda está na fila.
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 layer
The 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 |
|---|---|
get_brand_overview | High-level overview + taste primer |
get_magic_trick | Verbatim magic_trick.md |
get_positioning | Positioning document |
get_audience | Audience YAML, parsed |
get_messaging | Messaging document |
get_differentiation | Differentiation document |
get_concepts | Creative concepts/directions |
get_voice | Voice document |
get_colors_and_type | Colors + typography custom properties |
get_assets | Logos + brand assets |
get_fonts | Font faces |
get_components | UI primitives |
get_tokens | Token specimens |
get_motion | Motion system (json + css) |
get_css | colors_and_type.css + motion.css text |
search_brand | Full-text search |
validate_usage | Validate brand compliance |
get_context_diff | 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 | Brand overview |
brand://magic_trick | Taste primer |
brand://verbal/positioning | Positioning document |
brand://verbal/audience | Audience YAML |
brand://verbal/messaging | Messaging document |
brand://verbal/differentiation | Differentiation document |
brand://verbal/concepts | Creative concepts |
brand://verbal/voice | Voice document |
brand://visual/colors_and_type | Colors + typography CSS |
brand://visual/assets | Asset index |
brand://visual/fonts | Font face index |
brand://visual/components | Component index |
brand://visual/tokens | Token specimens |
brand://visual/motion | 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 |
|---|---|
base | Shared foundation -- fonts, core colors, global tokens |
web | Overrides for the public-facing website (agent/visual/artifacts/web/) |
product | Overrides for the SaaS application (agent/visual/artifacts/product/) |
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 |
|---|---|
brand/shared/colors/*.css | agent/visual/colors_and_type.css |
brand/shared/typography/*.css | agent/visual/colors_and_type.css |
brand/shared/logos/* | agent/visual/assets/ |
brand/shared/components/*.md | agent/visual/components/*.md |
brand/shared/voice/brand-voice.md | agent/verbal/voice.md |
brand/shared/guidelines/*.md | agent/verbal/{positioning,messaging,differentiation,concepts}.md |
brand/marketing/* | agent/visual/artifacts/web/* |
brand/product/* | agent/visual/artifacts/product/* |
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 UI for browsing the brand atomic system
docs Generate project documentation files
Global Options:
--version Show version number
--help Show help
Contributing
Contributions are welcome.
git clone https://github.com/ejwhite7/brandkit-mcp
cd brandkit-mcp
npm install
npm run build
npm test
- TypeScript strict mode
- ESM imports with
.jsextensions - No
anytypes -- use proper interfaces - Tests use Vitest
License
MIT -- see LICENSE for details.
Built with the Model Context Protocol by Anthropic.