_ registry / mcp streamable-http · checked 57m ago

screenrove

https://screenrove.com

Registry code: 263b4f43ad02ceb6

api record

Screenrove: real UI screenshots from 191 products (Developer tools, Design & creative, Docs & knowledge, AI tools, Whiteboards & diagrams, Project & work management and more), 6,950 screens: onboarding flows, pricing pages, settings, dashboards and marketing sites, each with notes, design-problem tags and a measured design guide. Coverage differs by product: list_products and get_product say what was captured (172 signed in, 19 logged out only).

Use it when the user says things like:

endpoint
https://screenrove.com/mcp
protocol
streamable-http ·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 screenrove live?
Yes — it answered the hub's last check (checked 57m ago). It answered 99% of checks over the last 30 days.
Is screenrove free to use?
Yes — the hub reached it with no key and no payment.
What tools does screenrove have?
24 tools: compare_pricing, check_my_ui, compare_screens, get_product, find_related_screens, build_handoff, build_recipe, get_motion, ….
Is screenrove 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
98.7%

90 days 99.4%· all time 99.4%

latency
1,198ms

last good check

priced tools
0

of 24 tools

_ answered our checks, 90 days 326 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
  • unknown → live
_ what it is for
topic
developer tools
used for
  • find ui reference screenshots
  • get a product's design guide
  • compare two product screens
  • get onboarding flows of real products
takes → gives
text → data, images
tools
13 reads
_ 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 24 tools
9 open 15 never probed 9 of 24 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_screens reads open 3h ago

    Find screens by design problem and keyword, e.g. "pricing page like Stripe", "settings", "empty project list". Every screen is tagged on four facets: task, pattern (screen archetype), component and state. Commas mean OR within a facet, facets combine with AND, e.g. pattern=list-view,table-view and state=empty; ids, labels or aliases work ("kanban", "zero state"); list_tags has the vocabulary. q matches titles, tags, visual style (dark, serif, editorial, gradient, playful, pastel...), notes, sections and actions; a word that names a tag ranks screens with that tag first. Screens matching more words rank higher; partial=true says none matched all, and a mistyped word is corrected (didYouMean). Each row has productName, captured date and the page url to cite. Results come 10 at a time (offset for more); fields=brief gives one line each. Near-duplicates (the same capture twice, a dark-theme copy) show once with the other ids in variants. Over MCP a small thumbnail of the top result is attached (720 px JPEG, fields=full); images=1 to 3 attaches 1x screenshots instead, images=0 none. Then look before building: get_screen_image for the 1x image of your picks, or build_recipe with 2 to 6 ids to get them as 1x images with measurements in one brief. The next field names the exact call.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "Keywords, e.g. \"pricing page\", \"empty state\", \"dark settings\", \"serif editorial landing\". Omit to list everything that matches the filters."
    },
    "kind": {
      "enum": [
        "flow",
        "marketing",
        "product"
      ],
      "type": "string",
      "description": "Only return this kind of screen."
    },
    "task": {
      "type": "string",
      "description": "What the person is trying to do, comma-separated for any of them, e.g. create, choose-plan, invite."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Results per page, 1 to 50."
    },
    "scope": {
      "enum": [
        "marketing",
        "public-demo",
        "task-incomplete",
        "signed-in"
      ],
      "type": "string",
      "description": "Only screens from collections with this capture scope."
    },
    "state": {
      "type": "string",
      "description": "Data or interaction state, comma-separated for any of them, e.g. empty, first-run, filtered, error."
    },
    "fields": {
      "enum": [
        "full",
        "brief"
      ],
      "type": "string",
      "default": "full",
      "description": "brief gives one line per screen, without notes and tags."
    },
    "images": {
      "type": "integer",
      "maximum": 3,
      "minimum": 0,
      "description": "How many of the top results' 1x screenshots to attach, 0 to 3. Unset, fields=full attaches one small thumbnail (720 px wide, about 18 KB) and fields=brief none; 0 attaches none."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Results to skip; pass nextOffset from the previous page."
    },
    "pattern": {
      "type": "string",
      "description": "Screen archetype, comma-separated for any of them, e.g. pricing-page, list-view, board-view, settings."
    },
    "product": {
      "type": "string",
      "description": "Only return screens from this product id, e.g. linear, stripe, airbnb."
    },
    "component": {
      "type": "string",
      "description": "Building blocks on the screen, comma-separated for any of them, e.g. modal, date-picker, comparison-table."
    }
  },
  "additionalProperties": false
}
    arguments 78 lines
  • list_products reads open 3h ago

    List the 191 products in the catalog, one compact line each: id, name, category, a one-line coverageLabel saying what was captured (signed in or logged out only), screen counts and page url. Paged (50 by default) and filterable by category or q; the first page also counts products per category. To find screens, search_screens is quicker.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "Words in the product's name, category or description."
    },
    "limit": {
      "type": "integer",
      "default": 50,
      "maximum": 200,
      "minimum": 1,
      "description": "Products per page, 1 to 200."
    },
    "detail": {
      "enum": [
        "brief",
        "full"
      ],
      "type": "string",
      "default": "brief",
      "description": "full adds description, tags and source."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Results to skip; pass nextOffset from the previous page."
    },
    "category": {
      "type": "string",
      "description": "A category or part of one, e.g. \"Developer tools\" or \"finance\"."
    }
  },
  "additionalProperties": false
}
    arguments 37 lines
  • get_motion_guidelines open 57m ago

    House rules for UI motion (durations, enter and exit easing, springs, reduced motion) with duration and easing tokens and the library's categories and triggers. Read it once before adding animation.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {},
  "additionalProperties": false
}
    arguments 6 lines
  • name_patterns open 9h ago

    How real products are named: pattern shares with examples, TLDs, domain styles, length and syllables, a per-category table and highlights such as the share of AI tools on .ai. Takes search_names' filters for one slice. Use it before proposing names.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "tld": {
      "type": "string",
      "description": "Comma-separated TLDs (OR)."
    },
    "length": {
      "type": "string",
      "description": "Letters in the name - a number or a range like 4-6."
    },
    "source": {
      "enum": [
        "library",
        "targets"
      ],
      "type": "string",
      "description": "library or targets."
    },
    "pattern": {
      "type": "string",
      "description": "Comma-separated naming patterns (OR) to summarise."
    },
    "category": {
      "type": "string",
      "description": "Comma-separated categories (OR) to summarise, e.g. \"AI tools\"."
    },
    "startsWith": {
      "type": "string",
      "description": "Letters the name starts with, or vowel or consonant."
    }
  },
  "additionalProperties": false
}
    arguments 35 lines
  • list_flows reads open 9h ago

    List captured user journeys (signup and onboarding, checkout, booking, search, marketplace, and task flows such as building a board) with step counts and flow type, 40 at a time. A flowType marked typeInferred was read from the flow's first steps; flows with no type are left out of a flowType filter and counted in untyped. get_flow gives the steps.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 40,
      "maximum": 100,
      "minimum": 1,
      "description": "Flows per page, 1 to 100."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Results to skip; pass nextOffset from the previous page."
    },
    "flowType": {
      "enum": [
        "signup-onboarding",
        "search",
        "checkout",
        "booking",
        "marketplace"
      ],
      "type": "string",
      "description": "Only return flows of this type. Untyped flows are counted, not shown."
    }
  },
  "additionalProperties": false
}
    arguments 31 lines
  • search_logos open 9h ago

    Logo references for designing a logo or app icon: each library product's own mark as its site serves it (never redrawn) with mark type, colours, shape, letter case, brand font and category, e.g. "lettermarks on a rounded tile", "green symbols". Logos are trademarks of their owners: study them, don't copy them.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "Words matched against product name, id, category and brand font; any word can match. More matched words rank first, then a name or category match above a font match, and rarer words above common ones."
    },
    "limit": {
      "type": "integer",
      "default": 24,
      "maximum": 169,
      "minimum": 1,
      "description": "Maximum results, 1 to 169."
    },
    "shape": {
      "type": "string",
      "description": "Comma-separated shapes (OR) - square tile, rounded tile, circle, freeform."
    },
    "colour": {
      "type": "string",
      "description": "Comma-separated colour families (OR) - red, orange, yellow, green, teal, blue, purple, pink,\nbrown, black, white, grey, or mono for single-colour glyphs that carry no colour."
    },
    "product": {
      "type": "string",
      "description": "Comma-separated product ids or names, e.g. linear,stripe."
    },
    "category": {
      "type": "string",
      "description": "Comma-separated categories (OR), e.g. \"Developer tools\", or \"ai\" for both AI categories."
    },
    "markType": {
      "type": "string",
      "description": "Comma-separated mark types (OR) - symbol, lettermark, wordmark, combination."
    },
    "lowercase": {
      "type": "boolean",
      "description": "Only letter-based marks whose letters are lowercase (true) or capitals (false)."
    },
    "includeMissing": {
      "type": "boolean",
      "default": false,
      "description": "Also list the library products that have no logo in the directory yet."
    }
  },
  "additionalProperties": false
}
    arguments 47 lines
  • search_names open 6h ago

    Naming ideas grounded in about 700 real product names, each with domain, TLD, category, naming pattern, length, syllables, casing and domain style (getX.com, Xhq.com…), plus stats for the whole match, e.g. "short invented names for AI tools on .ai". Traits are heuristics; check trademarks and domains before using a new name.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "Words matched against the name, domain, category and the product's own description; any word can match. Ranked by relevance unless sort is given - more matched words first, then a name or category match above a description match, and rarer words above common ones."
    },
    "tld": {
      "type": "string",
      "description": "Comma-separated TLDs (OR), e.g. ai,io or .com."
    },
    "sort": {
      "enum": [
        "relevance",
        "name",
        "length",
        "syllables"
      ],
      "type": "string",
      "description": "Order of results - relevance (the default with q), name (the default without q), length or syllables (shortest first)."
    },
    "limit": {
      "type": "integer",
      "default": 50,
      "maximum": 500,
      "minimum": 1,
      "description": "Maximum names, 1 to 500."
    },
    "length": {
      "type": "string",
      "description": "Letters in the name (spaces and punctuation not counted) - a number or a range like 4-6, -6 or 8-."
    },
    "source": {
      "enum": [
        "library",
        "targets"
      ],
      "type": "string",
      "description": "library (products Screenrove has captured) or targets (the Mobbin/Refero list)."
    },
    "dnsHint": {
      "type": "string",
      "description": "Optional and slower - up to 10 candidate domains, comma-separated (e.g. tallyho.com,tallyho.ai), each checked for DNS records over DNS-over-HTTPS. A hint, not a registrar check."
    },
    "pattern": {
      "type": "string",
      "description": "Comma-separated naming patterns (OR) - real-word, compound, blend, altered, suffix, prefix,\nacronym, alphanumeric, person-place, brand-extension, invented."
    },
    "category": {
      "type": "string",
      "description": "Comma-separated categories (OR), e.g. \"AI tools\", \"Developer tools\" or \"finance\"."
    },
    "syllables": {
      "type": "string",
      "description": "Syllables - a number or a range like 1-2."
    },
    "startsWith": {
      "type": "string",
      "description": "Letters the name starts with, or vowel or consonant."
    },
    "domainStyle": {
      "type": "string",
      "description": "Comma-separated domain styles (OR) - exact, prefixed, suffixed, domain-hack, subdomain, partial, different."
    }
  },
  "additionalProperties": false
}
    arguments 68 lines
  • search_motion open 6h ago

    Search the motion library: UI animations and micro-interactions (button presses, toggles, toasts, number tickers, check-offs, thinking states, hover effects, sounds) from open-source libraries and designers' recordings, each with an exact spec and most with vanilla code. Any word can match ("habit streak tick" finds check-offs); more matched words rank higher. Use it when an interactive element should feel finished, then get_motion for the spec and code. To audit a whole library: source=<id> fields=brief lists every entry in one call, with counts by category and by the source's own sections, and which code each has (vanilla, react, install, npm). For a whole UI, suggest_polish maps its parts to entries and sounds.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "Keywords, e.g. \"copy button\", \"toast\", \"number ticker\", \"thinking shimmer\"."
    },
    "basis": {
      "enum": [
        "code",
        "video",
        "rebuild"
      ],
      "type": "string",
      "description": "Where the numbers come from - code (exact, read from source), video (measured from a recording) or rebuild."
    },
    "limit": {
      "type": "integer",
      "default": 12,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum results, 1 to 50 (100 with fields=brief, its default)."
    },
    "fields": {
      "enum": [
        "full",
        "brief"
      ],
      "type": "string",
      "default": "full",
      "description": "brief gives one short row per entry (id, title, category, group, code), up to 100 per call."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Results to skip; pass nextOffset from the previous page."
    },
    "source": {
      "type": "string",
      "description": "Comma-separated source ids, as listed by get_motion_guidelines."
    },
    "hasCode": {
      "type": "boolean",
      "description": "Only entries with working code (a vanilla rebuild or original source)."
    },
    "trigger": {
      "type": "string",
      "description": "Comma-separated triggers (OR) - hover, press, click, focus, load, scroll, drag, state-change, loop, type."
    },
    "category": {
      "type": "string",
      "description": "Comma-separated categories (OR): button, toggle, input, list, card, navigation, overlay,\ntoast, loader, text, number, chat-ai, cursor, scroll, transition, icon, feedback, media,\nsound, other."
    }
  },
  "additionalProperties": false
}
    arguments 58 lines
  • list_tags open 57m ago

    List the tag vocabulary for searching by design problem: four facets (task, pattern, component, state), each tag with its definition, aliases and how many screens carry it. Use the ids with search_screens or pick_reference, e.g. pattern=board-view or state=empty.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "facet": {
      "enum": [
        "task",
        "pattern",
        "component",
        "state"
      ],
      "type": "string",
      "description": "Only return this facet."
    }
  },
  "additionalProperties": false
}
    arguments 17 lines
  • compare_pricing unknown 6h ago

    A fact table of 2 to 8 captured pricing pages, for research rather than building: per product, plan names and prices, cheapest paid plan with currency, monthly/yearly toggle and saving, free plan, trial, seat model, enterprise tier, notable limits, captured date and page url, plus a Markdown table. Values are as captured; a field the capture doesn't state is null and listed in missing (trial and seat model are quoted from the notes).

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "screens": {
      "type": "string",
      "description": "Comma-separated pricing screen ids, e.g. notion-marketing-pricing (search_screens with pattern=pricing-page)."
    },
    "products": {
      "type": "string",
      "description": "Comma-separated product ids, each compared by its captured pricing page, e.g. notion,slack,asana."
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • check_my_ui reads unknown 2d ago

    Compare the user's UI structure with the closest real products. Describe what they have (screen type, sections, flow steps, plan count; no personal names, prices or customer data) and get factual comparisons, not recommendations: plan counts, section order, blocks the references have that theirs lacks, flow length. image=true attaches the closest one's screenshot.

    mcp-tool

    {
  "type": "object",
  "required": [
    "description"
  ],
  "properties": {
    "kind": {
      "enum": [
        "flow",
        "marketing",
        "product"
      ],
      "type": "string",
      "description": "Only compare with this kind of capture."
    },
    "image": {
      "type": "boolean",
      "default": false,
      "description": "Attach the closest reference's 1x screenshot (MCP) or return its URL in image."
    },
    "limit": {
      "type": "integer",
      "default": 4,
      "maximum": 5,
      "minimum": 1,
      "description": "How many references to return, 1 to 5."
    },
    "product": {
      "type": "string",
      "description": "Only compare with this product id."
    },
    "flowType": {
      "enum": [
        "signup-onboarding",
        "search",
        "checkout",
        "booking",
        "marketplace"
      ],
      "type": "string",
      "description": "What the flow does, so step counts are only compared with flows of the same kind. Inferred from screenType when omitted."
    },
    "sections": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Page sections top to bottom, e.g. [\"Hero\", \"Plan cards\", \"FAQ\"]."
    },
    "flowSteps": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "For a multi-screen flow, each step's title in order, e.g. [\"Sign up\", \"Verify email\", \"Create workspace\"]."
    },
    "planCount": {
      "type": "integer",
      "description": "For pricing screens, how many plans are shown."
    },
    "screenType": {
      "enum": [
        "landing",
        "pricing",
        "feature-page",
        "sign-up",
        "sign-in",
        "verification",
        "onboarding-step",
        "plan-picker",
        "empty-state",
        "dashboard",
        "list",
        "detail",
        "create-form",
        "search",
        "picker",
        "booking",
        "checkout",
        "marketplace",
        "settings",
        "docs",
        "menu",
        "lesson"
      ],
      "type": "string",
      "description": "What kind of screen it is."
    },
    "description": {
      "type": "string",
      "description": "One or two sentences on what the screen is for and how it is laid out, e.g. \"Pricing page with three plan cards, a monthly/yearly toggle and a feature table\"."
    },
    "primaryAction": {
      "type": "string",
      "description": "The main button or action, e.g. \"Start free trial\"."
    }
  },
  "additionalProperties": false
}
    arguments 99 lines
  • compare_screens reads unknown 3h ago

    Compare two screens side by side (screen types, page sections, observed actions, dimensions, plan counts), e.g. Linear's pricing page with Stripe's, or one screen against a description of what the user is building (targetDescription).

    mcp-tool

    {
  "type": "object",
  "required": [
    "screenA"
  ],
  "properties": {
    "focus": {
      "enum": [
        "layout",
        "sections",
        "actions",
        "dimensions",
        "typography",
        "all"
      ],
      "type": "string",
      "default": "all",
      "description": "What aspects to emphasize in the comparison."
    },
    "screenA": {
      "type": "string",
      "description": "First screen id to compare, e.g. linear-marketing-pricing."
    },
    "screenB": {
      "type": "string",
      "description": "Second screen id to compare. If omitted, provide targetDescription instead."
    },
    "targetDescription": {
      "type": "string",
      "description": "Instead of screenB, describe what you're building to see how screenA matches, e.g. \"Pricing page with 3 tiers and a feature comparison table\"."
    }
  },
  "additionalProperties": false
}
    arguments 34 lines
  • get_product reads unknown 3d ago

    Get one product's collection: what was captured (coverageLabel, coverage, captureNote) and every screen, grouped into flow, marketing and product, one line each (id, title, primary pattern, page url). detail=full adds each screen's notes and tags. Use it to explore a competitor's whole UI; then get_screen_image on the screens you will build from, and get_design to match its look.

    mcp-tool

    {
  "type": "object",
  "required": [
    "productId"
  ],
  "properties": {
    "detail": {
      "enum": [
        "brief",
        "full"
      ],
      "type": "string",
      "default": "brief",
      "description": "full adds each screen's notes and tags."
    },
    "productId": {
      "type": "string",
      "description": "Product id from list_products, e.g. linear, stripe or airbnb."
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • find_related_screens unknown 3d ago

    Find screens from other products that solve the same design problem as this one: same primary pattern first, then shared tasks, states and components (rarer tags count more). At most two per product; each says why it matched, and a dark-theme copy folds into its row as variants. Use it after one good reference, e.g. other empty project lists or other pricing pages with a comparison table.

    mcp-tool

    {
  "type": "object",
  "required": [
    "screenId"
  ],
  "properties": {
    "kind": {
      "enum": [
        "flow",
        "marketing",
        "product"
      ],
      "type": "string",
      "description": "Only return this kind of screen."
    },
    "limit": {
      "type": "integer",
      "default": 6,
      "maximum": 20,
      "minimum": 1,
      "description": "Maximum results, 1 to 20."
    },
    "screenId": {
      "type": "string",
      "description": "Screen id from search_screens or get_product, e.g. linear-signup."
    },
    "sameProduct": {
      "type": "boolean",
      "default": false,
      "description": "Also include screens from the same product."
    }
  },
  "additionalProperties": false
}
    arguments 34 lines
  • build_handoff reads unknown 2d ago

    Build one product's reference as a complete prompt: ordered screens with notes, observed transitions, links to up to 10 agent-sized images (1x copies and section crops, each with its pixel size), the measured design guide and an implementation checklist; the same prompt as the site's "Use in agent" button. referenceId is `{product}-onboarding` (its flow), `{product}-collection` (everything) or one screen id. To combine screens from several products, use build_recipe.

    mcp-tool

    {
  "type": "object",
  "required": [
    "referenceId"
  ],
  "properties": {
    "goal": {
      "type": "string",
      "description": "What you want to build. Goes at the top of the prompt."
    },
    "stack": {
      "type": "string",
      "description": "Preferred stack, e.g. Next.js and Tailwind."
    },
    "screens": {
      "type": "string",
      "description": "Comma-separated screen ids to keep. Omit to include every screen in the reference."
    },
    "referenceId": {
      "type": "string",
      "description": "e.g. linear-onboarding, stripe-collection or vercel-marketing-pricing."
    },
    "includeDesign": {
      "type": "boolean",
      "default": true,
      "description": "Include the observed design guide. Set false to use your project's own design system."
    }
  },
  "additionalProperties": false
}
    arguments 30 lines
  • build_recipe unknown 3d ago

    The best way to build from references, with or without a person: pass 2 to 6 screen ids from search_screens (each "id: what to take from it") and get one Markdown brief with the screenshots attached at 1x (section crops for long pages), measured component sizes, the page structure and what to take from each. Up to 6 images are attached (one per reference, then extra section crops); the brief's first line lists them and names a get_screen_image call for any left out. Structure comes from the screens and every visual token from one style product, so conflicting looks are resolved instead of mixed. Interactive parts get matching motion entries to fetch with get_motion. E.g. Linear's issue composer, Vercel's pricing layout and Notion's look in one screen.

    mcp-tool

    {
  "type": "object",
  "required": [
    "screens"
  ],
  "properties": {
    "goal": {
      "type": "string",
      "description": "What you want to build. Goes at the top of the brief."
    },
    "stack": {
      "type": "string",
      "description": "Preferred stack, e.g. Next.js and Tailwind."
    },
    "style": {
      "type": "string",
      "description": "Product id whose measured visual language to use, e.g. linear or stripe. Omit to use the project's own design system."
    },
    "screens": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "1 to 6 screen ids, each optionally followed by \": what to take from it\", e.g. [\"linear-product-new-issue: issue composer modal\", \"vercel-marketing-pricing: plan cards and FAQ\"]."
    },
    "styleNotes": {
      "type": "string",
      "description": "Extra visual direction in words, e.g. \"our brand green #1a7f37, rounded corners\". Used on its own when style is omitted."
    },
    "styleContext": {
      "enum": [
        "marketing",
        "product"
      ],
      "type": "string",
      "description": "Which of the style product's guides to use. Defaults to marketing when most screens are marketing pages, otherwise product."
    }
  },
  "additionalProperties": false
}
    arguments 40 lines
  • get_motion unknown 2d ago

    Get one motion entry as a build prompt: what moves and how (every property, duration, easing or spring, delay and trigger), why it feels good, how to adapt it to another size, the accessibility it needs, Screenrove's vanilla HTML/CSS/JS and the original source where its license allows. Values are marked exact (code) or approximate (a recording). Keep the timings; scale distances to your element as the prompt says; translate the code to your stack.

    mcp-tool

    {
  "type": "object",
  "required": [
    "motionId"
  ],
  "properties": {
    "code": {
      "enum": [
        "both",
        "vanilla",
        "original",
        "none"
      ],
      "type": "string",
      "default": "both",
      "description": "Which code to include - both, vanilla (Screenrove rebuild), original (source library) or none."
    },
    "motionId": {
      "type": "string",
      "description": "Motion entry id from search_motion, e.g. interior-copy-button."
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
  • get_design reads unknown never probed

    Get a product's measured design guide: fonts, colour palette, type scale, layout and component observations, measured separately for its marketing site and product UI. Use it for "make it look like <product>" or "trustworthy like <product>": take the tokens from here and the structure from its screens (search_screens with product, then get_screen_image). fonts gives each context's families by role (display, body, mono) with licence, a CSS fallback stack and the closest free alternative plus its <link>; use the free one unless the user has the licensed font.

    mcp-tool

    {
  "type": "object",
  "required": [
    "productId"
  ],
  "properties": {
    "context": {
      "enum": [
        "marketing",
        "product"
      ],
      "type": "string",
      "description": "Which surface to return. Omit for both."
    },
    "productId": {
      "type": "string",
      "description": "Product id from list_products, e.g. linear, stripe or airbnb."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • get_screen reads unknown 2d ago

    Get everything recorded about one screen: notes on what it does and how it's laid out, product, captured date, page url, source URL, dimensions, observed actions and where they lead, and page sections for long marketing pages. The notes are not the screen: call get_screen_image with the same id to see it before building something similar.

    mcp-tool

    {
  "type": "object",
  "required": [
    "screenId"
  ],
  "properties": {
    "screenId": {
      "type": "string",
      "description": "Screen id from search_screens or get_product, e.g. linear-signup."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • get_screen_image reads unknown 2d ago

    See the screen; call it on your top picks before writing UI. preview (default) is 1x, so 1 image px = 1 CSS px (the top of a long page). The text gives its pixel size and a long page's sections: section=N returns one as a 1x crop. size=full is the original (often 2x), refused above 8000 px tall.

    mcp-tool

    {
  "type": "object",
  "required": [
    "screenId"
  ],
  "properties": {
    "size": {
      "enum": [
        "preview",
        "full"
      ],
      "type": "string",
      "default": "preview",
      "description": "preview (1x) or full (the original)."
    },
    "section": {
      "type": "string",
      "description": "One section of a long page, by number or title words, as a 1x crop."
    },
    "screenId": {
      "type": "string",
      "description": "Screen id from search_screens or get_product, e.g. linear-signup."
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • pick_reference reads unknown never probed

    Show a person 2 to 6 matching references side by side in their browser and let them click the one to build from. Returns a URL to open for them; then call wait_for_pick with the pickId for their choice and a build prompt. Only when a person is there to choose: autonomous agents should use build_recipe.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "q": {
      "type": "string",
      "description": "Search words, e.g. \"pricing page\", \"onboarding\", \"empty state\". The best matches become the options. Can be combined with tag filters, or left out when tag filters are given."
    },
    "goal": {
      "type": "string",
      "description": "What the user is building, shown on the page and used in the build prompt, e.g. \"NSDR premium upgrade page\"."
    },
    "kind": {
      "enum": [
        "flow",
        "marketing",
        "product"
      ],
      "type": "string",
      "description": "Only search this kind of screen."
    },
    "task": {
      "type": "string",
      "description": "Tag filter, as in search_screens, e.g. create."
    },
    "count": {
      "type": "integer",
      "default": 3,
      "maximum": 6,
      "minimum": 2,
      "description": "How many options to show when searching, 2 to 6."
    },
    "stack": {
      "type": "string",
      "description": "Preferred stack for the build prompt."
    },
    "state": {
      "type": "string",
      "description": "Tag filter, as in search_screens, e.g. empty."
    },
    "pattern": {
      "type": "string",
      "description": "Tag filter, as in search_screens, e.g. pricing-page."
    },
    "product": {
      "type": "string",
      "description": "Only search this product id."
    },
    "screens": {
      "type": "string",
      "description": "Comma-separated screen ids to show instead of searching, e.g. from an earlier search_screens."
    },
    "component": {
      "type": "string",
      "description": "Tag filter, as in search_screens, e.g. comparison-table."
    }
  },
  "additionalProperties": false
}
    arguments 59 lines
  • wait_for_pick reads unknown 2d ago

    Wait for the person to choose on the pick page. Long-polls up to 50 seconds and returns as soon as they click, or status "pending" (call again). Once chosen: their reference with its screenshot attached and a full build prompt. "dismissed" means none fit: ask what they want. A pick can be collected for 24 hours.

    mcp-tool

    {
  "type": "object",
  "required": [
    "pickId"
  ],
  "properties": {
    "wait": {
      "type": "integer",
      "default": 45,
      "maximum": 50,
      "minimum": 0,
      "description": "Seconds to wait for a choice, 0 to 50."
    },
    "pickId": {
      "type": "string",
      "description": "The pickId returned by pick_reference."
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • get_flow reads unknown 3d ago

    Get a product's captured flow: every step in order with title, notes, page url, observed transitions (button labels and where they lead) and which steps are alternate branches, plus the handoffId for build_handoff. Use it to study how a product structures signup, onboarding or a task; then get_screen_image on the steps you will copy.

    mcp-tool

    {
  "type": "object",
  "required": [
    "productId"
  ],
  "properties": {
    "productId": {
      "type": "string",
      "description": "Product id from list_products, e.g. linear, stripe or airbnb."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • suggest_polish unknown 57m ago

    Given the parts of a UI (elements, a description, or Screenrove screen ids; from a screenshot, list the parts you see), returns motion entries and sounds that would improve each part, plus new touches it doesn't have yet (additions), not only replacements. Then get_motion each one.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "sound": {
      "type": "boolean",
      "default": true,
      "description": "Include Cuelume sounds."
    },
    "screens": {
      "type": "string",
      "description": "Comma-separated Screenrove screen ids; their tagged components become the parts."
    },
    "sources": {
      "type": "string",
      "description": "Only these motion sources, e.g. \"interior,beautifului,cuelume\"."
    },
    "elements": {
      "type": "string",
      "description": "Comma-separated parts, e.g. \"save button, search field, results grid, toast, AI chat\"."
    },
    "description": {
      "type": "string",
      "description": "The UI in a sentence or two"
    }
  },
  "additionalProperties": false
}
    arguments 28 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 263b4f43ad02ceb6.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/263b4f43ad02ceb6/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/263b4f43ad02ceb6/badge.svg)](https://brick.blue/agent/263b4f43ad02ceb6?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.