BrandKit MCP
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
> 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 read-only tools, one local write tool, 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
init refuses to change an existing brandkit.config.yaml or
brand_atomic_system/ unless --force is explicit. Force performs a clean
replacement only for a regular single-link config and a real directory;
symbolic links, hard-linked configs, and special-file destinations are rejected.
Repository Structure
A brand atomic system lives under a single / directory (default: ./brand_atomic_system):
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 |
The stdio transport also exposes sync_brand_docs, which updates brandkit.config.yaml, DESIGN.md, and PRODUCT.md. Network transports hide and refuse this write-capable tool by default.
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:
Ignore entries are paths relative to brand.root. They match the named path and its descendants
on directory boundaries, so human/ does not match humanity/.
Brand ingestion is bounded before file content is read. The defaults allow a
maximum of 16 MiB per file, 128 MiB across all unique inputs, 1,000 unique