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

pcprice-watch

https://www.pcprice.watch

Registry code: ab5b66bc0d8fa9bb

api record

Real eBay sold prices for used PC parts (GPUs, CPUs, RAM, motherboards, PSUs) in the US, UK, Germany, France, Italy, Spain and Poland, refreshed every 8 hours. Use check_ebay_listing when the user shares an eBay listing link and asks whether it is a good price. Use get_used_price for 'what does a used X cost'. Cite page_url when quoting numbers.

endpoint
https://www.pcprice.watch/check/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 pcprice-watch live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is pcprice-watch free to use?
Yes — the hub reached it with no key and no payment.
What tools does pcprice-watch have?
3 tools: check_ebay_listing, get_used_price, list_tracked_models.
Is pcprice-watch 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
271ms

last good check

priced tools
0

of 3 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

_ 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.

  • list_tracked_models open 1h ago

    The PC part models pcprice.watch tracks, with their IDs, optionally filtered by part type.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "part_type": {
      "type": "string",
      "description": "optional filter: GPU, CPU, RAM, MOTHERBOARD, PSU, LAPTOP, IPHONE"
    }
  },
  "additionalProperties": false
}
    arguments 10 lines
  • check_ebay_listing unknown 1h ago

    Judge whether an eBay listing is a good price: compares its delivered price with what the same model actually sold for recently (great / fair / above typical / overpriced, and % vs the sold median), and lists cheaper listings that ship to the buyer.

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "the eBay listing link the user pasted (ebay.com, ebay.co.uk, ebay.de, ebay.fr, ebay.it, ebay.es, ebay.pl, or an ebay.us/ebay.io share link)"
    },
    "country": {
      "type": "string",
      "description": "the buyer's ISO 3166-1 alpha-2 country code, e.g. DE; used for delivered price and shipping. Ask the user if unknown"
    }
  },
  "additionalProperties": false
}
    arguments 17 lines
  • get_used_price unknown 1h ago

    What a used PC part actually sells for on eBay: sold-price median and p25-p75 range (EUR) over the last 30 and 90 days, for one market or all seven pooled.

    mcp-tool

    {
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "the part model, e.g. 'RTX 3060', 'RX 7900 XT', 'Ryzen 7 5800X'; call list_tracked_models if unsure"
    },
    "country": {
      "type": "string",
      "description": "ISO country code of one of the scraped markets (US, GB, DE, FR, IT, ES, PL); omit for all markets pooled"
    }
  },
  "additionalProperties": false
}
    arguments 17 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 ab5b66bc0d8fa9bb.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/ab5b66bc0d8fa9bb/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/ab5b66bc0d8fa9bb/badge.svg)](https://brick.blue/agent/ab5b66bc0d8fa9bb?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.