Alcheon
Server Details
Alcheon is an MCP server that gives AI coding agents access to a curated library of 100+ analyzed real-world design systems, letting them recommend reference sites, synthesize design briefs with spacing and color tokens, and generate section-level UI guidance — so AI-built interfaces draw from actual design DNA instead of generic defaults.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
get_section_inspiration1 field changed- changed
Input schema / properties / tokenSet / descriptionPrevious value: -"The CSS :root {} token set from generate_design_tokens. Paste the full token block. The section spec will reference these variables (var(--color-primary), var(--font-heading), etc.) instead of generating its own values."New value: +"REQUIRED: The COMPLETE, UNTRUNCATED CSS output from generate_design_tokens. Pass every single line of the token file verbatim — do NOT summarise, abbreviate, or cherry-pick tokens. The full file is needed so the section spec can reference every var() correctly (colors, typography, spacing, shadows, motion, buttons, cards, etc.). Partial token sets produce broken or inconsistent output."
1 tool update
- Changed
get_section_inspiration3 fields changed- added
Input schema / properties / avoidAdded value: +{ + "description": "Optional list of structural patterns or compositions to explicitly avoid. E.g. ['3-column grid', 'centered hero text', 'gradient background']. Use this to force divergence from previous results or steer away from overused layouts.", + "items": { + "type": "string" + }, + "type": "array" +} - added
Input schema / properties / classPrefixAdded value: +{ + "description": "Optional CSS class prefix for all generated class names. E.g. 'gvp2' → classes like .gvp2-hero, .gvp2-card. Prevents collisions when multiple sections coexist on one page.", + "type": "string" +} - added
Input schema / properties / targetWidthAdded value: +{ + "description": "Optional target container width in pixels. When set, the spec will scale layout values (padding, font sizes, gaps) appropriately for a constrained container instead of assuming full viewport width. E.g. 800 for an embedded panel, 1200 for a standard page.", + "type": "number" +}
1 tool update
- Changed
generate_design_tokens3 fields changed- removed
Input schema / properties / avoidRemoved value: -{ - "description": "Optional list of patterns to consciously avoid, even if common across reference sites. E.g. ['product_screenshots', 'hamburger_nav', 'hero_gradients', 'stats_section']", - "items": { - "type": "string" - }, - "type": "array" -} - removed
Input schema / properties / emphasizeRemoved value: -{ - "description": "Optional list of design aspects to emphasize from the reference sites. E.g. ['spacing_rhythm', 'gradient_hero', 'dark_sections', 'typography']", - "items": { - "type": "string" - }, - "type": "array" -} - changed
Input schema / properties / intent / descriptionPrevious value: -"A description of the UI you're designing. Be specific about: product type, target audience, mood, any hard constraints. E.g. 'A dark-themed SaaS dashboard for a developer monitoring tool. Target audience: backend engineers. Clean, data-dense, no marketing fluff.'"New value: +"What is the product and what vibe/mood should the design convey? Focus on identity, not page structure. Include: product type, target audience, aesthetic mood, any hard constraints. Do NOT list specific page sections (hero, pricing, etc.) — this tool generates the design system, not page architecture. E.g. 'A dark, premium SaaS for developer monitoring. Audience: backend engineers. Mood: data-dense, technical, no marketing fluff.' E.g. 'AI design intelligence tool for coding agents. Sophisticated, high-craft, dark UI with strong typographic hierarchy.'"
3 tool updates
- Added
generate_design_tokens - Changed
get_section_inspiration8 fields changed- added
Input schema / properties / contentAdded value: +{ + "description": "Optional actual content for the section — headlines, feature names, pricing tiers, testimonial quotes, FAQ items. When provided, the HTML skeleton will use this real content instead of placeholder slots.", + "type": "string" +} - changed
Input schema / properties / context / descriptionPrevious value: -"Optional context about what you're building. Helps tailor the recommendations. E.g. 'A developer tool landing page with a dark theme' or 'E-commerce site for sustainable fashion'"New value: +"Optional context about the project. E.g. 'A developer tool landing page' or 'B2B DevOps product with a dark UI'" - changed
Input schema / properties / maxExamples / descriptionPrevious value: -"Maximum number of real-world examples to include (default: 6)"New value: +"Maximum number of reference examples to analyze for structural patterns (default: 5)" - changed
Input schema / properties / maxExamples / maximumPrevious value: -15New value: +10 - changed
Input schema / properties / sectionType / descriptionPrevious value: -"The type of section or component to get inspiration for. E.g. 'how it works', 'pricing', 'hero', 'FAQ', 'testimonials', 'feature grid', 'stats counter', 'CTA banner', 'onboarding steps', 'comparison table'"New value: +"The type of section to build. E.g. 'hero', 'pricing', 'FAQ', 'testimonials', 'feature grid', 'stats counter', 'CTA banner', 'how it works', 'comparison table', 'footer'" - changed
Input schema / properties / sites / descriptionPrevious value: -"Optional list of specific site slugs to draw inspiration from. If omitted, searches all available sites. E.g. ['stripe_com', 'linear_app']"New value: +"Optional: restrict structural pattern search to specific site slugs. LEAVE BLANK in most cases — the tool searches all sites and produces more diverse, unexpected structures. Do NOT pass the same sites used as DNA for generate_design_tokens; those sites' aesthetic is already baked into the token set, so restricting structural search to them too creates an echo chamber. Only pass specific slugs when you explicitly want structure from a particular site (e.g. 'I want a Stripe-style pricing layout')." - added
Input schema / properties / tokenSetAdded value: +{ + "description": "The CSS :root {} token set from generate_design_tokens. Paste the full token block. The section spec will reference these variables (var(--color-primary), var(--font-heading), etc.) instead of generating its own values.", + "type": "string" +} - changed
Input schema / requiredPrevious value: -[ - "sectionType" -]New value: +[ + "sectionType", + "tokenSet" +]
- Removed
synthesize_brief
2 tool updates
- Removed
recommend_sites - Changed
synthesize_brief2 fields changed- changed
Input schema / properties / sites / descriptionPrevious value: -"Array of site slugs to draw inspiration from (use list_sites to see available options). E.g. ['stripe_com', 'linear_app', 'vercel_com']"New value: +"Array of site slugs to draw inspiration from (use list_sites to see available options). E.g. ['stripe_com', 'linear_app', 'vercel_com']. OMIT to auto-select — Alcheon scores all sites for relevance then applies a farthest-point diversity algorithm ensuring the set spans different visual approaches. Always prefer omitting over manually picking sites via search_sites, which lacks this diversity guarantee." - changed
Input schema / requiredPrevious value: -[ - "sites", - "intent" -]New value: +[ + "intent" +]
1 tool update
- Changed
recommend_sites1 field changed- removed
Input schema / properties / contrastRemoved value: -{ - "description": "When true, selects sites that OPPOSE each other on a key design axis rather than sites that agree. The response names the contrast axis — pass it as contrastAxis to synthesize_brief. Use this after a repetition warning, or when the user wants something genuinely unexpected.", - "type": "boolean" -}
9 tool updates
- First observed
get_component_examples - First observed
get_layout_blueprint - First observed
get_section_inspiration - First observed
get_site_overview - First observed
list_sites - First observed
recommend_sites - First observed
scrape_site - First observed
search_sites - First observed
synthesize_brief
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.169 npm1MIT
- AlicenseCqualityAmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs119 npm49 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceEnables tracking competitor websites, changelogs, blog feeds, and pricing pages with meaningful diffs, classification, and Markdown digests via MCP tools for listing, adding, removing competitors, running checks, and retrieving digests or changes.MIT

industrylens-mcpofficial
AlicenseNot gradedqualityBmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.