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

shop-nobi

https://api.nobi.ai

Registry code: d3e21c1b14c56dc1

api record

Shop Nobi searches the product catalogs of about 900 curated independent online stores, chosen for the quality of their catalogs: about 1.1 million products in all.

Unlike a general web search, search_products returns products that match the request, not web pages: each with its price, whether it is in stock, an image, and a direct link to its page on the store's own website. Store catalogs are kept constantly refreshed, so prices and stock are up to date.

endpoint
https://api.nobi.ai/v1/shop/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 shop-nobi live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is shop-nobi free to use?
Yes — the hub reached it with no key and no payment.
What tools does shop-nobi have?
2 tools: find_shop_nobi_page, search_products.
Is shop-nobi 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
213ms

last good check

priced tools
0

of 2 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

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 2 tools
2 never probed 0 of 2 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.

  • find_shop_nobi_page unknown 1h ago

    Finds a Shop Nobi web page about a product topic, such as "leather boots" or "linen dresses", to link to. It does not search products, so it is not the tool for a shopper's request to find or compare products. Each page lists matching products from many stores with a short buying guide. Returns the page's title, description and link only when its topic has the same words, allowing changes in word order, accents and singular or plural forms. Says when no matching page exists. It never substitutes a broader page. exactMatch is true for every returned page.

    mcp-tool

    {
      "type": "object",
      "required": [
        "topic"
      ],
      "properties": {
        "topic": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "The product topic, in a few plain words, such as \"leather boots\"."
        }
      }
    }
    arguments 14 lines
  • search_products unknown 1h ago

    Searches the product catalogs of curated independent online stores, chosen for the quality of their catalogs, for products that match the request. It fits requests to find, compare or choose products, such as "find me waterproof hiking boots under $200", gift ideas, or a specific product type or brand. Unlike a general web search, it returns products rather than web pages: each result is one product with its name, the store that sells it, its price and currency, whether it is in stock, an image, and a direct link to its page on the store's own website. Store catalogs are kept constantly refreshed, so prices and stock are up to date. Shop Nobi sells nothing itself: the user buys from the store. Links carry UTM tags that tell the store the visit came from Shop Nobi. When a product's linkLabel is set, such as "We may earn a commission", show it next to that product's link.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 20,
          "minimum": 1,
          "description": "How many products to return, from 1 to 20. The default is 10."
        },
        "query": {
          "type": "string",
          "maxLength": 500,
          "minLength": 1,
          "description": "What the user is looking for, in plain words, with the details that matter to them, such as \"waterproof hiking boots\" or \"linen dress for a summer wedding under $150\"."
        }
      }
    }
    arguments 21 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 d3e21c1b14c56dc1.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/d3e21c1b14c56dc1/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/d3e21c1b14c56dc1/badge.svg)](https://brick.blue/agent/d3e21c1b14c56dc1?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
60%

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.