_ registry / mcp streamable-http · checked 1h ago

kodshop-catalog

https://kodshop.cloud

Registry code: 915e99fcaca13e9a

api record

Catalog of KodShop (kodshop.cloud): gift cards, service top-ups, travel eSIM. Prices in RUB. Search with search_catalog, read denominations with get_product, then buy with buy_product — call it once to get x402 payment requirements (USDC on Base), sign them, and call it again with the same order_id and the signed payment_payload. Full API: https://kodshop.cloud/llms.txt.

endpoint
https://kodshop.cloud/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 kodshop-catalog live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is kodshop-catalog free to use?
Yes — the hub reached it with no key and no payment.
What tools does kodshop-catalog have?
3 tools: buy_product, get_product, search_catalog.
Is kodshop-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 99.5%· all time 99.5%

latency
189ms

last good check

priced tools
0

of 3 tools

_ answered our checks, 90 days 417 checks · signed record
  • degraded → live
_ what it is for
used for
  • search gift cards and esims
  • get product denominations and prices
  • buy a gift card or top-up
takes → gives
text, payments → data
tools
2 reads1 moves money
_ 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 3 tools
1 open 2 never probed 1 of 3 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_catalog reads open 8h ago

    Search the store catalog of gift cards, service top-ups and eSIM data plans. Returns matching products with their price, availability and product page URL.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "type": {
          "enum": [
            "voucher",
            "recharge_fixed",
            "recharge",
            "e_sim"
          ],
          "type": "string",
          "description": "voucher = gift card, recharge_fixed / recharge = top-up, e_sim = eSIM data plan."
        },
        "limit": {
          "type": "integer",
          "description": "Max products to return (default 10, max 50)."
        },
        "query": {
          "type": "string",
          "description": "Free text matched against product name and brand, e.g. \"steam\" or \"playstation\"."
        },
        "country": {
          "type": "string",
          "description": "ISO-3166-1 alpha-2 country code the product is issued for, e.g. US, TR."
        }
      }
    }
    arguments 27 lines
  • buy_product moves money unknown never probed

    Buy a gift card, service top-up or travel eSIM and receive the delivery. Paid in USDC on Base (x402), no account and no browser. Call it twice: first with the order arguments to get payment requirements and an order_id (nothing is charged), then with that order_id plus the signed x402 payment payload to settle and receive the code.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "email": {
          "type": "string",
          "description": "Delivery address. The code, eSIM profile or number is emailed here, and it is the only identity the order has. Required on the first call."
        },
        "amount": {
          "type": "number",
          "description": "Only for products where get_product reported requires_amount; send instead of item_id."
        },
        "item_id": {
          "type": "integer",
          "description": "Denomination id from get_product items[]."
        },
        "order_id": {
          "type": "string",
          "description": "Second call only: the order_id returned by the first call."
        },
        "quantity": {
          "type": "integer",
          "description": "Copies to buy. Defaults to 1 — send it only to buy several."
        },
        "product_id": {
          "type": "integer",
          "description": "Product id from search_catalog."
        },
        "product_type": {
          "enum": [
            "giftcard",
            "topup"
          ],
          "type": "string",
          "description": "giftcard = voucher, topup = service recharge. eSIM data plans from search_catalog are bought as giftcard too — the value names the order shape, not the goods."
        },
        "account_number": {
          "type": "string",
          "description": "Only for products where get_product reported requires_account: the recipient account the top-up credits."
        },
        "payment_payload": {
          "type": "object",
          "description": "Second call only: the signed x402 PaymentPayload built from the requirements the first call returned."
        }
      }
    }
    arguments 45 lines
  • get_product reads unknown 8h ago

    Get one catalog product by id: available denominations with prices, required order inputs, and any countries where the code cannot be redeemed.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "integer",
          "description": "Product id from search_catalog."
        }
      }
    }
    arguments 12 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 915e99fcaca13e9a.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/915e99fcaca13e9a/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/915e99fcaca13e9a/badge.svg)](https://brick.blue/agent/915e99fcaca13e9a?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
70%

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.