# Brandsystem MCP — Build [Health: Active]

**Category:** 🎯 Marketing  
**Repository:** https://github.com/Brandcode-Studio/brandsystem-mcp  
**GitHub Stars:** 15  
**npm Downloads (last month):** 1091  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/brandsystem-mcp-build

## Description
Build portable .brand runtimes from websites, Figma, and PDFs for use across AI tools.

## Tools
Capabilities this server exposes over MCP:

- **brand_start** — Adopt a brand into a portable .brand/ runtime from whatever source already exists: existing brand guidelines (PDF), a website URL, a Figma library, or a hosted Brandcode Studio brand. THE entry point when the user says 'use my existing brand guidelines with AI', 'I have a PDF brand guide', 'use our Figma library', 'create a brand system', 'extract brand from website', or 'set up brand guidelines'. Pass website_url, guideline_pdf, figma_file_key, or brandcode_url — or pass no source and it discovers local candidates and presents a menu with a privacy explanation. Set mode='auto' with a website_url to run the full pipeline (extract, compile DTCG tokens + design-synthesis.json + DESIGN.md + brand runtime + interaction policy, generate HTML report) in one call. If .brand/ already exists, returns current status with next steps. NOT for reading an already-compiled brand (use brand_runtime or brand_context) or for sharing an existing brand with a team (use brand_brandcode_connect).
- **brand_status** — Check brand system progress and get next steps. Shows what has been extracted (colors, fonts, logo), confidence levels, session completion status, and what to do next. Use when resuming a previous session, checking readiness, or when the user asks 'what's the state of my brand?' If no .brand/ exists, returns a full getting-started guide with all available tools. Returns structured status data.
- **brand_compile** — Generate DTCG design tokens, design-synthesis.json, DESIGN.md, brand runtime, and interaction policy from extracted brand data. Transforms core-identity.yaml into tokens.json, brand-runtime.json (single-document brand contract for AI agents), and interaction-policy.json (enforceable rules). When Session 2+ data exists, also generates visual-identity-manifest.md and system-integration.md. Use after brand_extract_web, brand_extract_site, brand_extract_visual, or brand_extract_figma. Returns token counts, clarification items, and file list.
- **brand_clarify** — Resolve an ambiguous brand value interactively. After brand_compile, some values need human confirmation — wrong primary color, unknown font, unassigned color roles. Pass the clarification item ID and the user's answer (hex color, role name, font name, or 'yes'/'no'). Supports natural language: 'the purple one is accent' or '#5544f2 is secondary'. Returns updated identity and remaining clarification count.
- **brand_report** — Generate a portable HTML brand identity report with embedded logos, color swatches, typography, and tokens. The HTML is self-contained and works offline — upload it to any AI chat (Claude, ChatGPT, Gemini) as instant brand guidelines. Written to .brand/brand-report.html. Use after brand_compile. Returns file path, report summary (color/font/logo counts), and a ready-to-copy Brand Instructions text block.
- **brand_preflight** — Check HTML/CSS against brand rules — catches off-brand colors, wrong fonts, missing logo, and anti-pattern violations (drop shadows, gradients, etc.). Pass an HTML string or file path. Mode 'check' (default) runs all compliance checks and returns pass/warn/fail per rule. Mode 'rules' lists all active preflight rules without checking content. Use after generating any visual content to validate brand compliance. Returns overall status and per-check details. NOT for scoring content copy — use brand_audit_content. NOT for brand directory validation — use brand_audit.
- **brand_runtime** — Read the compiled brand runtime contract (brand-runtime.json). Returns the brand system that AI agents load as context for on-brand output. Supports slicing: 'full' (~1200 tokens, everything), 'visual' (~200 tokens, colors + fonts + anti-patterns), 'voice' (~400 tokens, tone + vocabulary + perspective), 'minimal' (~100 tokens, primary color + heading font). Use slices when passing brand context to sub-agents — smaller context reduces token cost and agent satisficing. Live Mode aware: when enabled via brand_brandcode_live, the runtime refreshes from the hosted Brandcode runtime on each call (subject to cache TTL). Falls back silently to the local mirror on network error. Read-only. Run brand_compile to refresh.
- **brand_context** — Select a task-scoped brand context from the compiled runtime. THE tool to call first when the user says 'write this in our voice', 'write this LinkedIn post in our brand voice', 'make an on-brand social graphic', or 'build a landing page' — it returns only the governed rules relevant to that task instead of the full runtime. Deterministic: task_type maps to sections via a fixed table, audience matches governed personas exactly or reports no-match — no inference. Returns context (the selected brand slices), output_contract (required delivery shape), matched_selectors (what was chosen and why), and no_governed_match. NOT for reading the entire runtime (use brand_runtime) or checking finished content (use brand_check).
- **brand_check** — Inline brand linter — call this WHILE writing content or code, the way you call a type-checker. <50ms pass/fail on any combination of text (voice/never-say/AI-isms), color (palette match with ΔE distance), font (typography match), or css (anti-pattern violations). Designed for tight loops: write a sentence, brand_check it, fix, continue. Returns specific actionable fixes per failed input. Requires brand_compile to have run first. NOT a publish-time gate — use brand_check_compliance for the single PASS/FAIL verdict before shipping. NOT for 0-100 scoring — use brand_audit_content. NOT for HTML/CSS rule violations — use brand_preflight.
- **brand_brandcode_auth** — Activate Brandcode Studio connection for saving and pushing brands. Preferred mode: "activate" displays a short code (e.g. BRAND-7K4X) for the user to enter at brandcode.studio/activate — no copy-paste of tokens needed. Also supports: "status" (check auth), "login" (magic link fallback), "set_key" (manual token), "logout" (clear credentials). Use when the user wants to save their brand to Studio or says "activate", "connect to Brandcode", or "save my brand online". NOT needed for extraction, preview, or brand_check — those work without auth.
- **brand_brandcode_connect** — Connect a local .brand/ to Brandcode Studio. Two modes: "pull" (default) downloads an existing hosted brand by URL/slug. "save" uploads the local .brand/ to Studio (requires prior auth via brand_brandcode_auth). THE tool when the user says "make our brand available to my whole team", "share our brand with the team", "connect to Brandcode", "pull from Studio", "save brand to Studio", or "upload my brand". Returns brand name, slug, sync token, and connection details.
- **brand_export** — Bundle the compiled brand system into a portable artifact for a specific destination. Use when asked 'share my brand', 'export for ChatGPT/Cursor/team', 'generate brand guidelines', 'make a one-pager', or 'create a brand PDF'. Target 'chat': self-contained markdown for upload to any AI conversation (Claude, ChatGPT, Gemini). Target 'code': MCP server config + CLAUDE.md/.cursorrules snippet. Target 'team': human-readable brand guidelines for designers/writers/marketers. Target 'email': ~500-word summary for Slack or email. Target 'claude-skill': SKILL.md with embedded logo + rules for persistent Claude artifacts. Target 'pdf': branded PDF with swatches, type, anti-patterns, and voice. Set include_logo=false to drop the embedded SVG/data URI when size matters. Writes to .brand/exports/<file> and returns the full content (markdown targets) or a generation summary (pdf). Requires brand_compile to have run first. NOT for previewing one section — use brand_preview.

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

```json
"mcpServers": {
  "brandsystem-mcp-build": {
    "command": "npx",
    "args": ["-y","@brandsystem/mcp"]
  }
}
```

## Documentation

## What Brandsystem MCP — Build MCP server does

Brandsystem MCP — Build converts existing brand material into structured files that AI agents and design workflows can use. Sources include a website URL, PDF guidelines, a Figma library, local candidates, or a hosted Brandcode Studio brand. The resulting `.brand/` directory can contain core identity data, DTCG design tokens, a single-file `brand-runtime.json` contract, interaction policies, design synthesis data, an agent-readable design brief, extracted logo assets, and an offline HTML report.

The server covers the full adopt, use, and check workflow. It can discover or extract colors, fonts, and logos; compile those findings into reusable brand data; ask for confirmation when values are ambiguous; and produce task-specific context for writing, design, or implementation work. It also supports exporting the compiled system for AI chats, code projects, teams, email, PDFs, and Claude skills.

## How it works

Start with `brand_start`, optionally providing a website, guideline PDF, Figma file key, or Brandcode Studio URL. Automatic website mode can run extraction, compilation, report generation, and runtime creation in one operation. `brand_status` shows progress and identifies the next action when work is incomplete.

After extraction, `brand_compile` creates tokens and runtime files. `brand_clarify` resolves uncertain values such as color roles or font names. Use `brand_runtime` for the complete contract or a smaller visual, voice, or minimal slice. For task-specific work, `brand_context` selects governed rules and returns the matching selectors and output contract rather than passing the entire runtime.

Validation tools serve different stages. `brand_check` performs fast inline checks on text, colors, fonts, or CSS while content is being created. `brand_preflight` checks HTML or CSS for broader rule compliance, including off-brand colors, incorrect fonts, missing logos, and listed anti-patterns. `brand_report` creates a self-contained HTML report suitable for offline viewing or upload to an AI chat.

## Setup and configuration

Install the npm package with an MCP client installation command or add it to an MCP configuration using `npx`:

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

The package provides installation targets for Codex, Claude Code, Cursor, Windsurf, Claude Desktop, and Cline. The installer performs a dry run unless `--write` is supplied. Claude Desktop also supports a downloadable MCP bundle from the project's latest GitHub release, which asks for the folder containing the `.brand/` directory.

Authentication is optional for extraction, preview, and local checking. Call `brand_brandcode_auth` when saving or pushing a brand to Brandcode Studio, then use `brand_brandcode_connect` to pull a hosted brand or upload the local runtime. Local operation does not require an account.

## Tools and capabilities

- Adopt brand data from websites, PDFs, Figma, local candidates, or Brandcode Studio.
- Compile identity findings into DTCG tokens, runtime contracts, policies, and design artifacts.
- Select compact, task-specific context for agents and sub-agents.
- Check text, typography, colors, HTML, and CSS against brand rules.
- Generate offline reports and destination-specific exports, including chat, code, team, email, PDF, and Claude skill formats.
- Authenticate with Brandcode Studio and pull or save shared brand systems.

_Full upstream README: https://allmcps.com/mcp/brandsystem-mcp-build/readme_