_ registry / mcp + a2a streamable-http · checked 14m ago

parfum1-perfumes

https://parfum1.com

Registry code: a76e5d394a80dfa5

api record

parfum1 sells designer and niche perfumes as decants in 3, 10 and 30 ml (prices in EUR including VAT). Find a perfume with search_perfumes, read it with get_perfume (notes, every size with price and stock; the full bottle is always out of stock), browse houses with list_houses and get_house, and answer delivery, returns, payment and contact questions with get_store_info. Link customers to the product url in each answer; ordering happens on the website.

endpoint
https://parfum1.com/mcp
door code
d5be2f5b40ac70e4
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 parfum1-perfumes live?
Yes — it answered the hub's last check (checked 14m ago). It answered 100% of checks over the last 30 days.
Is parfum1-perfumes free to use?
Yes — the hub reached it with no key and no payment.
What tools does parfum1-perfumes have?
5 tools: get_perfume, get_house, list_houses, get_store_info, search_perfumes.
Is parfum1-perfumes 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
165ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
  • 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
1

through this hub

calls served
1

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
3 open 2 never probed 3 of 5 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_houses open 14m ago

    List the perfume houses in the catalogue, A to Z, with their handle, whether the house is a niche house, the number of perfumes and the house page URL. Optionally filter by words in the house name.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "query": {
          "type": "string",
          "maxLength": 100,
          "description": "Words in the house name, for example \"dior\"."
        }
      },
      "additionalProperties": false
    }
    arguments 12 lines
  • get_store_info open 14m ago

    Read how parfum1 works, with the same facts as its help pages: delivery (dispatch, cost, countries), returns, payment methods and contact details. Pass a topic for one, or none for all four.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "topic": {
          "enum": [
            "delivery",
            "returns",
            "payment",
            "contact"
          ],
          "type": "string",
          "description": "One of delivery, returns, payment, contact. Leave empty for all four."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • search_perfumes open 14m ago

    Search the parfum1 catalogue by words in the perfume name, house or scent family (all words must match, accents ignored), optionally within one house. Returns a page of perfumes in popularity order with the starting price, stock, rating and product URL.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "page": {
          "type": "integer",
          "default": 1,
          "minimum": 1,
          "description": "Page number, starting at 1."
        },
        "house": {
          "type": "string",
          "maxLength": 100,
          "description": "Only perfumes of this house: a house handle or name from list_houses, for example \"nishane\"."
        },
        "query": {
          "type": "string",
          "maxLength": 100,
          "description": "Words to find in the perfume name, house or scent family, for example \"oud\" or \"nishane hacivat\". Leave empty to list the catalogue."
        },
        "per_page": {
          "type": "integer",
          "default": 20,
          "maximum": 50,
          "minimum": 1,
          "description": "Perfumes per page, 1 to 50."
        }
      },
      "additionalProperties": false
    }
    arguments 30 lines
  • get_perfume unknown never probed

    Read one perfume by its handle: name, house, description, top, heart and base notes, and every size (3, 10 and 30 ml) with the price, the struck regular price, price per ml and whether it is in stock, exactly as the product page shows them, plus the full bottle (listed out of stock) and the product URL.

    mcp-tool

    {
      "type": "object",
      "required": [
        "handle"
      ],
      "properties": {
        "handle": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]*$",
          "maxLength": 200,
          "description": "The perfume handle from search_perfumes, for example \"hacivat-by-nishane\"."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • get_house unknown never probed

    Read one perfume house by its handle: its introduction, the number of perfumes and the first 50 of them with starting price and stock. Use search_perfumes with the house for the rest.

    mcp-tool

    {
      "type": "object",
      "required": [
        "handle"
      ],
      "properties": {
        "handle": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]*$",
          "maxLength": 200,
          "description": "The house handle from list_houses, for example \"nishane\"."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
_ try it over mcp 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 a76e5d394a80dfa5.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/a76e5d394a80dfa5/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/a76e5d394a80dfa5/badge.svg)](https://brick.blue/agent/a76e5d394a80dfa5?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 knowoff the mcp door
card completeness
90%

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
1
ok
1
failed
0
success rate
100%
median latency
104ms
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
—

1 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.