brand_audit
Validate .brand/ directory for completeness and correctness.
How to use it
Project documentation lists brand_audit for the Brandsystem MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Brandsystem MCP
npx @brandsystem/mcp install --client codex --writeOther tools in Brandsystem MCP (33)
Score content against brand rules (0-100) across multiple dimensions.
Detect systematic brand drift across multiple pieces of content.
Connect a local .brand/ directory to a hosted Brandcode Studio brand and pull the current package.
Toggle connected read tools to refresh from the hosted runtime within a short cache TTL.
Inspect the current Brandcode Studio connection, sync history, and local package summary.
Pull updates from a previously connected hosted brand using sync-token-aware delta behavior.
Define buyer journey stages (ships with 4 proven defaults).
Generate messaging variants for every persona x journey stage combination.
Build buyer personas through a 7-question guided interview.
Define editorial content themes balanced across awareness, engagement, and conversion.
Quick pass/fail compliance gate before publishing.
Resolve ambiguous brand values interactively (color roles, font confirmations).
Generate DTCG design tokens, brand runtime contract, and interaction policy from extracted data.
Define perspective, voice codex (tone, vocabulary, AI-ism detection), and brand story.
Select a task-scoped slice of the runtime deterministically (tasktype → sections, audience → persona match, compact budget). Returns matched selectors and explicit no-match — never silent fallback.
Define composition rules, patterns, illustration style, and anti-patterns (6 interview sections).
Generate portable brand files for Chat, Code, team sharing, or email.
Extract from Figma design files (higher accuracy). Two-phase: plan then ingest.
Audit existing website voice -- fingerprint, vocabulary, claims, AI-isms, gaps.
Discover representative pages, render them across desktop and mobile, capture screenshots, sample multiple components, and persist extraction-evidence.json.
Screenshot the rendered page in headless Chrome and extract computed colors, fonts, and visual context from JS-heavy sites.
Extract logo (SVG/PNG), colors, and fonts from any website URL.
Report bugs, friction, or feature ideas to the brandsystem team.
Generate design-synthesis.json and DESIGN.md from extracted evidence or the current brand state.
Scan and catalog brand assets with MANIFEST.yaml metadata.
Low-level directory scaffolding. Prefer brandstart instead.
Check HTML/CSS against brand rules -- catches off-brand colors, wrong fonts, anti-pattern violations.
Generate portable HTML brand report. Upload to any AI chat as instant guidelines.
Read the compiled brand runtime contract (single-document brand context for AI agents).
Add/replace logo via SVG markup, URL, or data URI.
Begin here. Creates a brand system from a website URL in under 60 seconds. Use mode='auto' for one-call setup with rendered and deep-site fallback on weak JS-rendered sites.
Check progress, get next steps, or see a getting-started guide if no brand exists yet.
Load full brand context (visual + voice + strategy) for content generation.