_ registry / mcp streamable-http · checked 11h ago

spartoo

https://www.spartoo.com

Registry code: 31a693db5593a275

api record

Product catalog of the www.spartoo.com online store (shoes, clothing, bags, accessories). Tools: list_filters (available brands, colors, sizes, categories and price range of a search), search_products (paginated product search with a free-text query, filtered by gender, brand, color, size and price, sorted by relevance, price, novelty or discount) and get_product (full details of products: sizes in stock, description, photos, other colors). Typical flow: list_filters -> search_products -> get_product. Prices are in EUR. Each product has a URL to its page on the store.

endpoint
https://www.spartoo.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 spartoo live?
Yes — it answered the hub's last check (checked 11h ago). It answered 100% of checks over the last 30 days.
Is spartoo free to use?
Yes — the hub reached it with no key and no payment.
What tools does spartoo have?
3 tools: search_products, list_filters, get_product.
Is spartoo 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
466ms

last good check

priced tools
0

of 3 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

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 3 tools
3 never probed 0 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_products unknown 11h ago

    Search the product catalog (shoes, clothing, bags, accessories) with a free-text query, as a shopper would type it in the search box of the site, in the language of the site (e.g. "baskets nike femme rouges"). The query is analysed like on the site: brand, category, color and gender words become filters, the remaining words are a text search. Optional arguments override what was found in the query for the same filter (brand, color, size, gender) or refine it (sort, price range in the currency of the site). Typical flow: list_filters to discover the available brands / colors / sizes of a search, then search_products with those exact values, then get_product for the details (sizes in stock, description, photos) of a chosen product. Results are paginated: use page and page_size, and request the next page while has_more is true. applied_filters tells how the query was understood and which filters were really applied, with their source (argument or query); the price range is rounded outward to the price steps of the catalog.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "page": {
          "type": "integer",
          "default": 1,
          "maximum": 100,
          "minimum": 1,
          "description": "Page number, starting at 1."
        },
        "size": {
          "type": [
            "string",
            "number",
            "array"
          ],
          "items": {
            "type": [
              "string",
              "number"
            ],
            "maxLength": 32,
            "minLength": 1
          },
          "maxItems": 10,
          "description": "Size label, or list of size labels (any of them), as displayed on the site: shoe sizes in EU (\"38\", \"42.5\" or \"42 1/2\"), clothing sizes (\"M\", \"XL\", \"38\", \"10 ans\"). Only products with this size in stock are returned. A half size also matches the neighbouring whole sizes. Use the sizes returned by list_filters."
        },
        "sort": {
          "enum": [
            "relevance",
            "price_asc",
            "price_desc",
            "newest",
            "discount"
          ],
          "type": "string",
          "default": "relevance",
          "description": "Sort order: relevance (default ranking of the site), price_asc, price_desc, newest, discount (highest discount first)."
        },
        "brand": {
          "type": [
            "string",
            "array"
          ],
          "items": {
            "type": "string",
            "maxLength": 64,
            "minLength": 1
          },
          "maxItems": 10,
          "description": "Brand name, or list of brand names (any of them), e.g. \"Nike\" or [\"Nike\", \"adidas\"]. Case and accents are ignored. Overrides the brand found in the query. Use the names returned by list_filters."
        },
        "color": {
          "type": [
            "string",
            "array"
          ],
          "items": {
            "enum": [
              "white",
              "black",
              "grey",
              "beige",
              "brown",
              "red",
              "burgundy",
              "pink",
              "orange",
              "yellow",
              "green",
              "khaki",
              "blue",
              "navy",
              "purple",
              "gold",
              "silver",
              "multicolor"
            ],
            "type": "string"
          },
          "maxItems": 10,
          "description": "Color, or list of colors (any of them), among: white, black, grey, beige, brown, red, burgundy, pink, orange, yellow, green, khaki, blue, navy, purple, gold, silver, multicolor. Overrides the color found in the query."
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Free-text search, e.g. brand, category, color, gender words (\"red nike sneakers for women\")."
        },
        "gender": {
          "enum": [
            "men",
            "women",
            "kids",
            "girls",
            "boys"
          ],
          "type": "string",
          "description": "Gender of the products. Overrides the gender found in the query. men and women include unisex products; kids includes girls and boys."
        },
        "page_size": {
          "type": "integer",
          "default": 20,
          "maximum": 50,
          "minimum": 1,
          "description": "Number of products per page."
        },
        "price_max": {
          "type": "number",
          "description": "Maximum price, in the currency of the site. Rounded up to the nearest price step.",
          "exclusiveMinimum": 0
        },
        "price_min": {
          "type": "number",
          "minimum": 0,
          "description": "Minimum price, in the currency of the site. Rounded down to the nearest price step."
        }
      },
      "additionalProperties": false
    }
    arguments 123 lines
  • list_filters unknown 11h ago

    List the values available to refine a search, with the same criteria as search_products (without sort and pagination): brands, colors, sizes, genders, categories (with product counts when known), price range and the total number of products (count_products). Use it before search_products to offer choices or to check that a value exists: brand names, colors and size labels returned here can be passed as is to the brand, color and size arguments of search_products (to filter on a category, add its name to the query). The values of a filter that is already applied are listed as if it was not, so that alternatives are visible. A very broad search (no category, brand or known word) is refused with a message: refine the query first.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "size": {
          "type": [
            "string",
            "number",
            "array"
          ],
          "items": {
            "type": [
              "string",
              "number"
            ],
            "maxLength": 32,
            "minLength": 1
          },
          "maxItems": 10,
          "description": "Size label, or list of size labels (any of them), as displayed on the site: shoe sizes in EU (\"38\", \"42.5\" or \"42 1/2\"), clothing sizes (\"M\", \"XL\", \"38\", \"10 ans\"). Only products with this size in stock are returned. A half size also matches the neighbouring whole sizes. Use the sizes returned by list_filters."
        },
        "brand": {
          "type": [
            "string",
            "array"
          ],
          "items": {
            "type": "string",
            "maxLength": 64,
            "minLength": 1
          },
          "maxItems": 10,
          "description": "Brand name, or list of brand names (any of them), e.g. \"Nike\" or [\"Nike\", \"adidas\"]. Case and accents are ignored. Overrides the brand found in the query. Use the names returned by list_filters."
        },
        "color": {
          "type": [
            "string",
            "array"
          ],
          "items": {
            "enum": [
              "white",
              "black",
              "grey",
              "beige",
              "brown",
              "red",
              "burgundy",
              "pink",
              "orange",
              "yellow",
              "green",
              "khaki",
              "blue",
              "navy",
              "purple",
              "gold",
              "silver",
              "multicolor"
            ],
            "type": "string"
          },
          "maxItems": 10,
          "description": "Color, or list of colors (any of them), among: white, black, grey, beige, brown, red, burgundy, pink, orange, yellow, green, khaki, blue, navy, purple, gold, silver, multicolor. Overrides the color found in the query."
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "Free-text search, e.g. brand, category, color, gender words (\"red nike sneakers for women\")."
        },
        "gender": {
          "enum": [
            "men",
            "women",
            "kids",
            "girls",
            "boys"
          ],
          "type": "string",
          "description": "Gender of the products. Overrides the gender found in the query. men and women include unisex products; kids includes girls and boys."
        },
        "price_max": {
          "type": "number",
          "description": "Maximum price, in the currency of the site. Rounded up to the nearest price step.",
          "exclusiveMinimum": 0
        },
        "price_min": {
          "type": "number",
          "minimum": 0,
          "description": "Minimum price, in the currency of the site. Rounded down to the nearest price step."
        }
      },
      "additionalProperties": false
    }
    arguments 97 lines
  • get_product unknown 11h ago

    Get the full details of one product (product_id) or of up to 10 products (product_ids), using the ids returned by search_products: description, price, sizes with their availability (in_stock, and the price of a size when it differs from the product price), photos, other colors of the same model (with their product ids) and characteristics (materials, heel height, country of origin...). Call it before recommending a product for a given size. Ids of products that do not exist or are no longer sold are listed in not_found.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "product_id": {
          "type": "integer",
          "minimum": 1,
          "description": "Id of the product (field id of search_products). Use either product_id or product_ids."
        },
        "product_ids": {
          "type": "array",
          "items": {
            "type": "integer",
            "minimum": 1
          },
          "maxItems": 10,
          "description": "Ids of several products (at most 10), to compare them."
        }
      },
      "additionalProperties": false
    }
    arguments 20 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 31a693db5593a275.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/31a693db5593a275/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/31a693db5593a275/badge.svg)](https://brick.blue/agent/31a693db5593a275?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.