_ registry / mcp streamable-http · checked 25m ago

eneui-catalog

https://ui.eneawork.it

Registry code: 00bec26d885c917f

api record

Search a catalog of 100k React/Tailwind/shadcn components. Call search_components with the UI you need, then get_component for the install command. Pages are also available as Markdown via get_page.

endpoint
https://ui.eneawork.it/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 eneui-catalog live?
Yes — it answered the hub's last check (checked 25m ago). It answered 100% of checks over the last 30 days.
Is eneui-catalog free to use?
Yes — the hub reached it with no key and no payment.
What tools does eneui-catalog have?
10 tools: search_components, get_component, search_blocks, get_design_system, list_design_systems, compose_page, get_page, check_licence, ….
Is eneui-catalog 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
221ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 1 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 10 tools
1 open 9 never probed 1 of 10 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.

  • list_categories open 25m ago

    List catalog categories with the number of components in each, so an agent can browse instead of guessing queries.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • search_components unknown never probed

    Find an existing React/Tailwind/shadcn component instead of writing one from scratch. Call this first for any UI task: modal, pricing table, animated hero, form, dashboard card. Every result carries the licence and the one-line install command, so the code can ship inside a client project.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "How many results (default 10)."
    },
    "query": {
      "type": "string",
      "description": "The job, not the name: 'pricing table with annual toggle', 'modal with focus trap', 'animated hero'."
    },
    "library": {
      "type": "string",
      "description": "Optional library id, e.g. keyline, aceternity, icons-lucide."
    },
    "category": {
      "type": "string",
      "description": "Optional category slug, e.g. button, modal, pricing."
    }
  }
}
    arguments 26 lines
  • get_component unknown never probed

    Read one component by library + name: description, license, page URL and the install command.

    mcp-tool

    {
  "type": "object",
  "required": [
    "library",
    "name"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "library": {
      "type": "string"
    }
  }
}
    arguments 15 lines
  • search_blocks unknown never probed

    Find a whole page section (hero, pricing, navbar, footer, testimonial, FAQ) instead of assembling one by hand. A block is a complete section published as `registry:block`, not a single component. Use this when the task is 'build the page', and check_licence before shipping a block to a client.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "How many results (default 10)."
    },
    "query": {
      "type": "string",
      "description": "What the section must do: 'pricing three tiers', 'hero with video', 'footer with newsletter'."
    },
    "source": {
      "type": "string",
      "description": "Optional registry id (e.g. shadcn, shadcn-ui-blocks)."
    }
  }
}
    arguments 22 lines
  • get_design_system unknown never probed

    Return design tokens (colours, typography, radius, shadows, spacing) plus agent instructions, so generated UI stays visually consistent. Call this before composing a page.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Theme slug (e.g. minimal-dark). Omit for the default."
    }
  }
}
    arguments 9 lines
  • list_design_systems unknown never probed

    List the available design systems with one-line descriptions.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • compose_page unknown never probed

    Compose a page from real catalogue blocks. Returns an ordered plan with block slugs, page URLs, dependencies and constraints, not generated code.

    mcp-tool

    {
  "type": "object",
  "required": [
    "intent"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1
    },
    "theme": {
      "type": "string",
      "description": "Design system slug to apply."
    },
    "intent": {
      "type": "string",
      "description": "What the page is for."
    },
    "pageType": {
      "type": "string",
      "description": "landing, pricing, dashboard, auth, ecommerce, blog"
    },
    "sections": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional explicit section roles, in order."
    }
  }
}
    arguments 32 lines
  • get_page unknown never probed

    Fetch any catalog page as Markdown (a component, a category hub, a library page, an article). Use the same paths as the site, e.g. /components/cat/modal or /blog.

    mcp-tool

    {
  "type": "object",
  "required": [
    "path"
  ],
  "properties": {
    "path": {
      "type": "string",
      "description": "Site path, e.g. /components/cat/modal"
    }
  }
}
    arguments 12 lines
  • check_licence unknown 25m ago

    Check whether a library may be shipped inside a client project. Reads the repository's licence file and returns the detected SPDX id, the repository, the sha256 of that file, the check date and a safe_for_commercial_delivery flag. A library whose licence could not be read comes back as unverified — never assume it is permissive. Call this before delivering code that contains a third-party library.

    mcp-tool

    {
  "type": "object",
  "required": [
    "library"
  ],
  "properties": {
    "library": {
      "type": "string",
      "description": "Library id, e.g. aceternity, icons-lucide, shadcn, magicui."
    }
  }
}
    arguments 12 lines
  • get_block unknown 25m ago

    Read one block by source + name: description, file list, registry dependencies and where it is published.

    mcp-tool

    {
  "type": "object",
  "required": [
    "source",
    "name"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "source": {
      "type": "string"
    }
  }
}
    arguments 15 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 00bec26d885c917f.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/00bec26d885c917f/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/00bec26d885c917f/badge.svg)](https://brick.blue/agent/00bec26d885c917f?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.