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

watch.diy

https://mcp.watch.diy

Registry code: afe3e2c0261ebca3

api record

watch.diy shows prices and store availability of DIY and garden products at German retailers (OBI, Bauhaus, toom, Hornbach, hagebau, Globus), based on the retailers' pages.

endpoint
https://mcp.watch.diy/public/mcp
protocol
http-sse ·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 watch.diy live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is watch.diy free to use?
Yes — the hub reached it with no key and no payment.
What tools does watch.diy have?
2 tools: where_to_buy_nearby, find_product.
Is watch.diy 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
252ms

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.

  • where_to_buy_nearby unknown never probed

    Checks the availability of 1-3 products (EANs) at every OBI, Bauhaus, toom, Hornbach, hagebau and Globus store within radiusKm (1-30, default 10) of a German postal code, based on the retailers' pages. Returns per product and retailer: status (read; not_listed_in_our_data = watch.diy knows no listing of this product at that retailer, which may still sell it; no_store_in_radius), the retailer's product name, its product page url, price with priceAsOf (a price older than 35 days is returned as null with priceNote), online with onlineAsOf (orderable or not_orderable: whether the retailer sells it online or to order, for the whole retailer and not a store; null when unknown or older than 35 days), and stores [{name, city, zip, km, state, updated}]. Store state is one of available, not_available, not_sold_in_store, unknown: available (the retailer's page shows it as available at that store), not_available (the retailer's page shows it as not available at that store; it does not mean the store never carries it), not_sold_in_store (the retailer does not sell it in that store), unknown (no information for that store). updated is "recently" (within the last 24 hours) or a date (YYYY-MM-DD). Also returns partial (true when there is no information for some stores), location {plz, radiusKm} and a notice. Can take a few seconds. Limits: public lookups are limited per client and per day. Errors: invalid_request (names the field and the reason, e.g. an unknown postal code), quota_exceeded (with the minutes until it can be tried again), public_unavailable.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "products",
        "plz"
      ],
      "properties": {
        "plz": {
          "type": "string",
          "pattern": "^\\d{5}$",
          "description": "German postal code (PLZ), 5 digits"
        },
        "products": {
          "type": "array",
          "items": {
            "type": "string",
            "pattern": "^\\d{8,14}$"
          },
          "maxItems": 3,
          "minItems": 1,
          "description": "1-3 EANs (GTIN barcodes, 8-14 digits), each once"
        },
        "radiusKm": {
          "type": "number",
          "default": 10,
          "maximum": 30,
          "minimum": 1,
          "description": "Kilometres around the postal code, 1-30 (default 10)"
        }
      },
      "additionalProperties": false
    }
    arguments 33 lines
  • find_product unknown 1h ago

    Searches watch.diy's index of DIY and garden products at German retailers (OBI, Bauhaus, toom, Hornbach, hagebau, Globus and more) by product name, EAN or manufacturer part number (MPN), and returns up to `limit` (1-5, default 3) products, best match first. Per product: name, brand, its EANs and per retailer the retailer's product name, its product page url and price with priceAsOf (when the price was read; a price older than 35 days is returned as null with priceNote). Only products the retailers sell themselves and still list online; store availability is not part of this answer: use where_to_buy_nearby with an EAN from here and a German postcode. Also returns match (ean, identifier, hybrid or text: how the query was answered) and a notice. When nothing matches, products is empty and message says what the index covers. Limits: public lookups are limited per client. Errors: invalid_request (names the field and the reason), quota_exceeded (with the minutes until it can be tried again), public_unavailable.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 3,
          "maximum": 5,
          "minimum": 1,
          "description": "Products to return, 1-5 (default 3)"
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "minLength": 2,
          "description": "Product name or description (any language, typos tolerated), an EAN (8 or 13 digits) or a manufacturer part number (MPN)"
        }
      },
      "additionalProperties": false
    }
    arguments 23 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 afe3e2c0261ebca3.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/afe3e2c0261ebca3/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/afe3e2c0261ebca3/badge.svg)](https://brick.blue/agent/afe3e2c0261ebca3?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.