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.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
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
Frequently Asked Questions
Claiming proves that you control a remote MCP connector. It does not move, proxy, or interrupt the server.
Open the connector listing, choose Claim ownership, and sign in to Glama.
Complete one verification method:
GitHub identity — fastest for official registry listings. For a namespace such as
io.github.alice/server, link the matching GitHub user, then choose Claim with GitHub. An organization namespace such asio.github.acme/serveralso needs that organization to have installed the Glama AI GitHub App and approved its permissions, because GitHub discloses organization membership only to apps it has installed. Use HTTP or DNS when it has not.HTTP challenge — works when you can deploy a public file. Generate a token, publish the exact JSON Glama shows at
/.well-known/glama.jsonon the same origin as the connector, then choose Check HTTP challenge.DNS challenge — works when you control DNS but cannot change the server. Generate a token, create the exact TXT record Glama shows, wait for it to propagate, then choose Check DNS challenge.
After verification, Glama sends a confirmation email and gives you access to listing details, thumbnails, health checks, and analytics. Keep the HTTP file or DNS record in place: Glama periodically checks it and ownership remains verified while the token is discoverable.
The HTTP ownership file has this structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"claim": "glama_claim_..."
}Claim tokens are opaque, stable, and bound to the signed-in Glama account. They contain no email address or other personal information. If Glama can no longer discover a verified HTTP or DNS token, it starts a seven-day grace period before removing claim-based access. Restore the same token during that period to keep ownership verified. Never publish an email address, Glama session token, GitHub token, or connector credential as ownership proof.
If verification fails, confirm that you copied the current token exactly. The HTTP file must be public, return valid JSON with a successful HTTP response, and stay on the connector's origin. DNS changes may need more time to propagate. A claim cannot transfer to a different origin or hostname: if the connector target changes, Glama starts the grace period and the new target must be claimed separately after the previous claim is released.
For a connector linked to the official MCP Registry, registry updates continue to replace its name, description, and URL by default. After claiming, open Manage connector and enable Use Glama listing details as the source of truth if edits made on Glama should be preserved. Categories and thumbnails are always managed on Glama; registry linkage and technical connection settings continue to sync.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
To improve your MCP server's ranking:
Claim ownership of the server listing
Complete the server profile with an accurate description and thumbnail
Provide a test profile so Glama can connect to and evaluate the server
Keep tool definitions clear and complete to earn a high Tool Definition Quality Score (TDQS)
Route real usage through the Glama Gateway; more recorded successful server uses also improve the ranking
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables detection and analysis of pre-public product launches through web search, content extraction, AI-powered scoring, and automated alerting. Provides comprehensive tools for surfacing stealth startup signals before they trend publicly.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- AlicenseNot gradedqualityCmaintenanceEnables AI chat clients to perform market research and competitive intelligence by gathering company overviews, competitor lists, product portfolios, pricing snapshots, and recent news via live Tavily search.MIT
- AlicenseAqualityAmaintenanceDetects hiring intent signals by scanning job boards for specific companies. Returns structured role data for outbound sales targeting.11961MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.
TSQS
Score is being calculated.