Raven MCP
未认领Design intelligence MCP server — principles, patterns, tokens, and strategy for AI-generated UI
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'raven-mcp' -- 'npx' '-y' 'raven-mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
40 个工具中显示 40 个
文档中列出的工具 (40)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
audit_consistency
Corpus/multi-page audit — compares ≥2 pages and flags cross-page divergence in content-container width and hero heading tier, inferring the canonical (modal) value from the corpus when no token is supplied — catching relational defects that single-page audits miss
audit_content
Per-item content verdicts (pass/warn/fail) for headings, prose, CTAs, labels, captions, metrics & outcomes against UX-writing principles + deterministic heuristics (metric needs number+unit; CTA action-led ≤4 words; prose flags passive/jargon/hedging; caption-vs-heading duplication) — with a before→
audit_contrast
Compute WCAG contrast for rendered text with tri-state status (pass, fail, indeterminate), effective backdrops, ratio ranges, and delta-to-pass only where the backdrop is determinate
audit_device_frame
Flag cropped content in device-mockup frames — frames (container box + intrinsic media + object-fit, or a DevTools snippet) detects object-fit:cover crop loss when frame AR ≠ media AR; clips (first/last frame PNGs) detects baked-in pan/zoom (Ken Burns); edgeframes (PNGs) flags content truncated at a
audit_ios_privacy
Audit Info.plist (or Expo app.json) /PRIVACY.md/entitlements/source — usage-string honesty, ATS, Android permissions, bundled secrets, undisclosed default data-egress
audit_ios_screen
Score a rendered iOS screen from an accessibility/view-hierarchy snapshot — 44pt targets + contrast + rhythm, in points
audit_layout
Evaluate visual rhythm, alignment, and optical balance; detects orphan-stretch (a lonely last-row grid/flex card stretching far wider than siblings)
audit_page
Audit HTML/CSS against Raven's quality standards — pass html for static audit, or url to render headless with optional scrollsettle (step through reveal gates, then return to top) and viewport parameters; containerMaxWidth makes container checks token-aware. Also flags inline SVG icons that hardcode
audit_responsive_visibility
Render a URL at multiple breakpoints and flag content elements that are visible on desktop but hidden on mobile (display:none/opacity:0/zero-size) — categorises each as likely-oversight (content vanishing on mobile) vs intentional (decorative)
audit_rn
Audit React Native / Expo source — touchable a11y labels, 44/48pt+hitSlop targets, font scaling, SafeAreaView, dark mode, against iOS HIG + Android Material
audit_swiftui
Audit SwiftUI source against Apple HIG — Dynamic Type, semantic colors, 44pt targets, 4/8pt spacing, AccentColor
audit_tap_targets
WCAG 2.5.5 / Apple 44pt web tap-target audit — enumerates every interactive element (rendered URL or snapshot) and emits a per-element fix table: selector, role, text, measured w/h, per-axis pixel deficit, and a concrete CSS fix, sorted worst-first
audit_typography
Typographic-scale report over rendered DOM text nodes (or a supplied snapshot) — detects the dominant modular-scale ratio and flags off-scale sizes, checks line-height consistency vs the body rhythm, and flags weight ladders >4 weights or non-standard values. Goes beyond auditpage's pass/fail typogr
audit_url
Render a live URL at each viewport×theme, scroll-settle, fire interactions, capture real pixels + DOM, then run the page/contrast/responsive/blank-media checks plus sliced-image edge-symmetry and hover-state white-wash detection over the captures — every finding tagged confirmed/likely-artifact/inco
audit_video_playback
Render a page and observe whether each <video> actually advances — samples currentTime, readyState, error codes, and autoplay-block state, then classifies each clip into playing
compose_system
Mix tokens from different systems
evaluate_design
Evaluate a design description against principles. Pass base64 PNG screenshots (beforescreenshot/afterscreenshot) for a structured before/after pixel diff with fixconfirmed, changedratio, and changed region. Pass compact: true to return only scores and violations (drops full principle/pattern bodies)
generate_design_system
Generate a custom design system from a brand color
generate_service_blueprint
Render a service blueprint as HTML — current state, or current vs. ideal side-by-side
get_brand_principles
Get brand/visual principles — logo, gradient, imagery, hierarchy, brand-as-system
get_brand_system
Get a full system styled like a well-known brand
get_brand_trends
Get current (2026) brand and visual-design trends with usage guidance
get_business_strategy
Get business/monetization strategies
get_checklist
Get a pre-publish checklist for a UI type
get_content_pattern
Get copy recipes for error messages, empty-state copy, notifications, form validation
get_content_principles
Get UX-writing principles — clarity, active voice, error anatomy, inclusive language
get_content_system
Get a brand's voice attributes, tone shifts, vocabulary, grammar, and content patterns
get_d4d_framework
Get Design for Delight framework templates
get_design_system
Get tokens for a specific design system
get_metrics_framework
Get a product-metrics framework — HEART, AARRR, North Star, conversion funnel, RICE, OKRs
get_pattern
Get proven patterns for a specific UI type
get_principles
Get design principles relevant to a UI context
get_research_method
Get qualitative, quantitative, or usability research methods with protocols and checklists
get_service_pattern
Get a service design pattern — blueprinting, human handoff, signup-as-service, omnichannel, moments of truth
get_service_standard
Get the GOV.UK Service Standard — 14 points for evaluating service quality
list_content_systems
Browse brand voice & tone systems (Conversational Product Voice, GOV.UK, Shopify Polaris, Atlassian)
list_design_systems
Browse available design systems
score_page
Return a per-category (0–10) design score for a page — typography, accessibility, spacing, color, responsive layout, design tokens, structure — derived from the same checks as auditpage, plus the overall score/grade, the weakest category, and categories Raven does not mechanically assess (brand, con
search_knowledge
Search across all principles, patterns, and strategies
suggest_contrast_fix
Given failing WCAG color pairs, return the minimal fg/bg change that clears the AA/AAA target — concrete passing values to fix auditcontrast failures