Endpoints: 76,849MCP servers: 32,728Payout addresses: 3,825Paid calls: 6,148Letters: 84Defects: 3,890counted 1 min ago
teppi

Server definition

Hash
sha256:3f6e6a145a51e43c8de5d0b8b5d71b88dd7ec144003bcc2f589ceb4c373d9f6c
What it is
What a remote MCP server returned when asked what it offers: 8 tools

The blob, as servednamed by its sha256

{ "instructions": "Emblematic gives your AI coding agent the real design system of a well-designed website: the fonts, colors, type scale, spacing, radii, shadows and layout read from its live page, as a DESIGN.md or tokens.\nWorkflow: search_designs, find_similar or browse_by to find references (search_sections for one part of a page: a hero, a pricing table, a footer) (each result comes with a screenshot: look at them to judge the look and pick) → get_design (screenshot and card first; ask for more sections only when needed) → get_design_md to fetch the file → save it to disk in the user's project → implement from the saved file.\nRule: copy exact values from the saved spec or DESIGN.md. Never transcribe values from memory or paraphrase them, and never read colors or sizes off a screenshot when a value exists: screenshots show the look, the values give the exact numbers. Where a section lists \"unconfirmed\" colors, the screenshot is the reference for those. Fields marked unverified (accent, section kinds) are heuristics; say so.\nUse references for direction and map them onto the project's existing design system; do not clone a brand's logo, copy or imagery.", "tools": [ { "description": "Use this to explore what the index contains: without `value` it lists the values of a facet with counts (e.g. every font family, every style tag); with `value` it lists the sites that have it, with a screenshot of each. Facets: font, color (hue bucket or \"neutral\"), style (derived tags), stack (framework/CMS/host), scheme, hero (hero layout), accent_strategy. Not for multi-criteria queries (use search_designs).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "facet": { "description": "Facet to browse.", "enum": [ "font", "color", "style", "stack", "scheme", "hero", "accent_strategy" ], "type": "string" }, "limit": { "default": 20, "maximum": 50, "minimum": 1, "type": "integer" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "previews": { "default": true, "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only.", "type": "boolean" }, "value": { "description": "A value from the facet listing, e.g. \"Inter\", \"blue\", \"pill\", \"next.js\".", "maxLength": 80, "type": "string" } }, "required": [ "facet" ], "type": "object" }, "name": "browse_by", "outputSchema": null }, { "description": "Use this when the user wants a direction that mixes references (\"Linear's colors with Stripe's type\"), or a ready-to-save brief from one site. Returns a markdown brief with exact values (role colors and site tokens, font stacks, type styles, radii, spacing, shadows, motion), caveats and source links. Deterministic: values are copied from the specs, nothing is invented. By default the 1st site gives color, the 2nd type, the 3rd layout; override with color_from/type_from/layout_from. Save the result to disk before implementing. Not for a single site's raw values (use get_design or get_design_md).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "color_from": { "description": "Site that supplies the palette (must be in `sites`).", "maxLength": 200, "minLength": 1, "type": "string" }, "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "layout_from": { "description": "Site that supplies layout, shape, depth and motion (must be in `sites`).", "maxLength": 200, "minLength": 1, "type": "string" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "notes": { "maxLength": 500, "type": "string" }, "product": { "description": "What is being built, e.g. \"pricing page for a dev-tools startup\".", "maxLength": 120, "type": "string" }, "sites": { "description": "1–3 indexed sites.", "items": { "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\").", "maxLength": 200, "minLength": 1, "type": "string" }, "maxItems": 3, "minItems": 1, "type": "array" }, "type_from": { "description": "Site that supplies typography (must be in `sites`).", "maxLength": 200, "minLength": 1, "type": "string" } }, "required": [ "sites" ], "type": "object" }, "name": "compose_brief", "outputSchema": null }, { "description": "Use this when the user likes one site and wants alternatives or neighbours: \"more like Linear\", \"sites with Stripe's typography\". Ranks indexed sites by an explainable distance on palette, type or layout (or the mean, \"overall\"), says why each is close and shows a screenshot of each. Not for free-text search (use search_designs).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "by": { "default": "overall", "description": "Which axis to compare on.", "enum": [ "overall", "palette", "type", "layout" ], "type": "string" }, "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "limit": { "default": 5, "maximum": 10, "minimum": 1, "type": "integer" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "previews": { "default": true, "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only.", "type": "boolean" }, "site": { "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\").", "maxLength": 200, "minLength": 1, "type": "string" } }, "required": [ "site" ], "type": "object" }, "name": "find_similar", "outputSchema": null }, { "description": "Use this when you need the actual design values of one indexed site to build or restyle UI. Default returns the desktop screenshot and the compact card (role colors with the site's own CSS variable names, fonts, type sizes, radius, container, caveats, links, screenshot URLs). Request more with `sections` (color, type, space, shape, depth, layout, motion, components, sections, stack, provenance) or \"full\" for the raw spec.json (large: ~15–20 KB). Not for search (use search_designs) or for a file to save in the project (use get_design_md).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "screenshot": { "default": "desktop", "description": "Which above-the-fold screenshot to attach as an image (default desktop). Full-page and dark-mode shots are linked in the card.", "enum": [ "desktop", "mobile", "both", "none" ], "type": "string" }, "sections": { "default": [ "card" ], "description": "Which parts to return. Default [\"card\"]. Ask only for what the task needs.", "items": { "enum": [ "card", "color", "type", "space", "shape", "depth", "layout", "motion", "components", "sections", "stack", "provenance", "full" ], "type": "string" }, "maxItems": 13, "minItems": 1, "type": "array" }, "site": { "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\").", "maxLength": 200, "minLength": 1, "type": "string" } }, "required": [ "site" ], "type": "object" }, "name": "get_design", "outputSchema": null }, { "description": "Use this when you will implement from a site's design: returns the file to save into the project verbatim. format \"design.md\" (default) is a DESIGN.md (YAML tokens + prose, google/design.md format); \"tokens.css\" is CSS custom properties; \"tailwind\" is a Tailwind v4 @theme block; \"shadcn\" is the :root/.dark variables shadcn/ui reads plus its @theme inline block; \"dtcg\" is W3C Design Tokens (DTCG 2025.10) JSON. Unverified values (e.g. a gated accent) are never put in a role slot; every format lists them under \"unverified\". Save the text to disk unchanged and work from the saved file. Not for answering questions about a site (use get_site or get_design).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "format": { "default": "design.md", "description": "Which file to return.", "enum": [ "design.md", "tokens.css", "tailwind", "shadcn", "dtcg" ], "type": "string" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "site": { "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\").", "maxLength": 200, "minLength": 1, "type": "string" } }, "required": [ "site" ], "type": "object" }, "name": "get_design_md", "outputSchema": null }, { "description": "Use this to answer \"what font/colors/framework does <site> use?\" for one site. Returns brand name, fonts with roles and weights, role colors, hues, detected stack (framework, CMS, hosting) and capture date. If the site is not indexed it says so (found: false) with the closest indexed sites. Not for building UI from the spec (use get_design).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "site": { "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\").", "maxLength": 200, "minLength": 1, "type": "string" } }, "required": [ "site" ], "type": "object" }, "name": "get_site", "outputSchema": null }, { "description": "Use this when the user wants design references: \"dark dev-tool sites\", \"sites using Söhne\", \"a warm serif editorial look\", \"something with #5E6AD2\". Matches brand, font, style tags, hue/hex, stack and description across the Emblematic index and returns small cards (scheme, key colors, fonts, radius, one-line summary) with a screenshot of each site. Look at the screenshots before picking. All filters are optional and combine with AND. Not for fetching one known site (use get_design) or listing facet values (use browse_by).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "color": { "description": "Hex (\"#5E6AD2\", ΔE match against role and palette colors) or hue name (\"blue\", \"green\", \"neutral\").", "maxLength": 40, "type": "string" }, "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "font": { "description": "Font family substring, accent-insensitive (\"inter\", \"sohne\").", "maxLength": 80, "type": "string" }, "limit": { "default": 8, "description": "Max results (default 8).", "maximum": 20, "minimum": 1, "type": "integer" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "previews": { "default": true, "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only.", "type": "boolean" }, "query": { "description": "Free text, e.g. \"dark mono minimal\", \"inter pill buttons\", \"next.js\".", "maxLength": 200, "type": "string" }, "scheme": { "description": "Page color scheme.", "enum": [ "light", "dark" ], "type": "string" }, "style": { "description": "Style tag: monochrome, single-accent, serif-display, pill, sharp, rounded, flat, layered-shadows, blur-nav, gradients, dark-mode…", "maxLength": 40, "type": "string" } }, "type": "object" }, "name": "search_designs", "outputSchema": null }, { "description": "Use this when the user wants examples of one part of a page: \"dark pricing sections\", \"hero with a product screenshot\", \"testimonials\". Returns homepage sections by kind, layout and visual tags, each with its own values (heading/body type, colors, buttons) and a screenshot. Each color is checked against the screenshot; a color it did not confirm is left out and named in `values.unconfirmed`, so take that part from the image. Not for whole sites (use search_designs).", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "context": { "description": "A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details.", "type": "string" }, "conversation_id": { "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.", "type": "string" }, "kind": { "description": "Section kind.", "enum": [ "hero", "nav", "features", "feature-detail", "bento", "product-showcase", "logos", "testimonials", "stats", "pricing", "comparison", "faq", "integrations", "code-sample", "blog", "gallery", "team", "newsletter", "cta", "footer" ], "type": "string" }, "limit": { "default": 8, "description": "Max results (default 8).", "maximum": 20, "minimum": 1, "type": "integer" }, "llm_model": { "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.", "type": "string" }, "previews": { "default": true, "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only.", "type": "boolean" }, "query": { "description": "Free text over description, tags, heading, fonts and site, e.g. \"serif headline\", \"gradient\".", "maxLength": 200, "type": "string" }, "scheme": { "description": "The section's own background.", "enum": [ "light", "dark" ], "type": "string" }, "site": { "description": "Only sections of this indexed site (slug, URL or brand name).", "maxLength": 200, "type": "string" } }, "type": "object" }, "name": "search_sections", "outputSchema": null } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:3f6e6a145a51e43c8de5d0b8b5d71b88dd7ec144003bcc2f589ceb4c373d9f6c | sha256sum