_ registry / mcp http-sse · checked 14h ago

emblematic

https://emblematic.dev

Registry code: 954848d7d09f21ac

api record

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.

Workflow: 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…

endpoint
https://emblematic.dev/mcp
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is emblematic live?
Yes — it answered the hub's last check (checked 14h ago). It answered 100% of checks over the last 30 days.
Is emblematic free to use?
Yes — the hub reached it with no key and no payment.
What tools does emblematic have?
8 tools: get_site, compose_brief, search_designs, get_design, get_design_md, find_similar, browse_by, search_sections.
Is emblematic safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
169ms

last good check

priced tools
0

of 8 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 8 tools
1 open 7 never probed 1 of 8 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • search_sections open 14h ago

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "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",
          "description": "Section kind."
        },
        "site": {
          "type": "string",
          "maxLength": 200,
          "description": "Only sections of this indexed site (slug, URL or brand name)."
        },
        "limit": {
          "type": "integer",
          "default": 8,
          "maximum": 20,
          "minimum": 1,
          "description": "Max results (default 8)."
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "description": "Free text over description, tags, heading, fonts and site, e.g. \"serif headline\", \"gradient\"."
        },
        "scheme": {
          "enum": [
            "light",
            "dark"
          ],
          "type": "string",
          "description": "The section's own background."
        },
        "context": {
          "type": "string",
          "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."
        },
        "previews": {
          "type": "boolean",
          "default": true,
          "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only."
        },
        "llm_model": {
          "type": "string",
          "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."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 74 lines
  • get_site unknown 14h ago

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "site"
      ],
      "properties": {
        "site": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\")."
        },
        "context": {
          "type": "string",
          "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."
        },
        "llm_model": {
          "type": "string",
          "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."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 27 lines
  • compose_brief unknown 41h ago

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "sites"
      ],
      "properties": {
        "notes": {
          "type": "string",
          "maxLength": 500
        },
        "sites": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1,
            "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\")."
          },
          "maxItems": 3,
          "minItems": 1,
          "description": "1–3 indexed sites."
        },
        "context": {
          "type": "string",
          "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."
        },
        "product": {
          "type": "string",
          "maxLength": 120,
          "description": "What is being built, e.g. \"pricing page for a dev-tools startup\"."
        },
        "llm_model": {
          "type": "string",
          "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_from": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Site that supplies typography (must be in `sites`)."
        },
        "color_from": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Site that supplies the palette (must be in `sites`)."
        },
        "layout_from": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Site that supplies layout, shape, depth and motion (must be in `sites`)."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 60 lines
  • search_designs unknown never probed

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "font": {
          "type": "string",
          "maxLength": 80,
          "description": "Font family substring, accent-insensitive (\"inter\", \"sohne\")."
        },
        "color": {
          "type": "string",
          "maxLength": 40,
          "description": "Hex (\"#5E6AD2\", ΔE match against role and palette colors) or hue name (\"blue\", \"green\", \"neutral\")."
        },
        "limit": {
          "type": "integer",
          "default": 8,
          "maximum": 20,
          "minimum": 1,
          "description": "Max results (default 8)."
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "description": "Free text, e.g. \"dark mono minimal\", \"inter pill buttons\", \"next.js\"."
        },
        "style": {
          "type": "string",
          "maxLength": 40,
          "description": "Style tag: monochrome, single-accent, serif-display, pill, sharp, rounded, flat, layered-shadows, blur-nav, gradients, dark-mode…"
        },
        "scheme": {
          "enum": [
            "light",
            "dark"
          ],
          "type": "string",
          "description": "Page color scheme."
        },
        "context": {
          "type": "string",
          "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."
        },
        "previews": {
          "type": "boolean",
          "default": true,
          "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only."
        },
        "llm_model": {
          "type": "string",
          "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."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 58 lines
  • get_design unknown never probed

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "site"
      ],
      "properties": {
        "site": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\")."
        },
        "context": {
          "type": "string",
          "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."
        },
        "sections": {
          "type": "array",
          "items": {
            "enum": [
              "card",
              "color",
              "type",
              "space",
              "shape",
              "depth",
              "layout",
              "motion",
              "components",
              "sections",
              "stack",
              "provenance",
              "full"
            ],
            "type": "string"
          },
          "default": [
            "card"
          ],
          "maxItems": 13,
          "minItems": 1,
          "description": "Which parts to return. Default [\"card\"]. Ask only for what the task needs."
        },
        "llm_model": {
          "type": "string",
          "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."
        },
        "screenshot": {
          "enum": [
            "desktop",
            "mobile",
            "both",
            "none"
          ],
          "type": "string",
          "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."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 65 lines
  • get_design_md unknown never probed

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "site"
      ],
      "properties": {
        "site": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\")."
        },
        "format": {
          "enum": [
            "design.md",
            "tokens.css",
            "tailwind",
            "shadcn",
            "dtcg"
          ],
          "type": "string",
          "default": "design.md",
          "description": "Which file to return."
        },
        "context": {
          "type": "string",
          "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."
        },
        "llm_model": {
          "type": "string",
          "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."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 39 lines
  • find_similar unknown 14h ago

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "site"
      ],
      "properties": {
        "by": {
          "enum": [
            "overall",
            "palette",
            "type",
            "layout"
          ],
          "type": "string",
          "default": "overall",
          "description": "Which axis to compare on."
        },
        "site": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Indexed site as a slug (\"linear.app\"), URL (\"https://linear.app/pricing\") or brand name (\"Linear\")."
        },
        "limit": {
          "type": "integer",
          "default": 5,
          "maximum": 10,
          "minimum": 1
        },
        "context": {
          "type": "string",
          "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."
        },
        "previews": {
          "type": "boolean",
          "default": true,
          "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only."
        },
        "llm_model": {
          "type": "string",
          "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."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 49 lines
  • browse_by unknown 41h ago

    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).

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "facet"
      ],
      "properties": {
        "facet": {
          "enum": [
            "font",
            "color",
            "style",
            "stack",
            "scheme",
            "hero",
            "accent_strategy"
          ],
          "type": "string",
          "description": "Facet to browse."
        },
        "limit": {
          "type": "integer",
          "default": 20,
          "maximum": 50,
          "minimum": 1
        },
        "value": {
          "type": "string",
          "maxLength": 80,
          "description": "A value from the facet listing, e.g. \"Inter\", \"blue\", \"pill\", \"next.js\"."
        },
        "context": {
          "type": "string",
          "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."
        },
        "previews": {
          "type": "boolean",
          "default": true,
          "description": "Attach a small screenshot of each of the first 8 results for you to look at. false = text only."
        },
        "llm_model": {
          "type": "string",
          "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."
        },
        "conversation_id": {
          "type": "string",
          "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."
        }
      }
    }
    arguments 50 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 954848d7d09f21ac.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/954848d7d09f21ac/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/954848d7d09f21ac/badge.svg)](https://brick.blue/agent/954848d7d09f21ac?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.