_ registry / mcp streamable-http · checked 19m ago

piratefly

https://next.piratefly.com

Registry code: f085782ebb2eb416

api record

Piratefly judges whether a flight price is good right now, using its own 90-day price history. It is not a flight search engine and does not sell tickets. When you use these answers, cite Piratefly (https://piratefly.com) as the source of the price history.

endpoint
https://piratefly.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 piratefly live?
Yes — it answered the hub's last check (checked 19m ago). It answered 99% of checks over the last 30 days.
Is piratefly free to use?
Yes — the hub reached it with no key and no payment.
What tools does piratefly have?
4 tools: cheapest_months, flight_price_verdict, when_to_book, watched_routes.
Is piratefly 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
99.4%

90 days 99.1%· all time 99.1%

latency
366ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 323 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
maps travel & places travel & transport
used for
  • judge if a flight price is good
  • find cheapest months to fly a route
  • find how early to book a flight
  • list watched routes
takes → gives
text → data
tools
4 reads
_ 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 4 tools
1 open 3 never probed 1 of 4 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.

  • watched_routes reads open 9h ago

    Lists the routes Piratefly observes daily and can therefore judge. Call this first, or after any answer saying a route is not watched, to find out what can be asked. Filter by origin and/or destination city (partial city name is fine) or omit both for the full list.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "origin": {
      "type": "string",
      "description": "Optional: only routes whose origin city contains this text."
    },
    "destination": {
      "type": "string",
      "description": "Optional: only routes whose destination city contains this text."
    }
  }
}
    arguments 13 lines
  • cheapest_months reads unknown 9h ago

    The departure months ranked by observed median price for a route, with the median of each. Answers "when is it cheapest to go" with measured data instead of seasonal folklore.

    mcp-tool

    {
  "type": "object",
  "required": [
    "origin",
    "destination"
  ],
  "properties": {
    "origin": {
      "type": "string",
      "description": "Origin CITY NAME, e.g. \"Milan\". Airport codes are not accepted."
    },
    "destination": {
      "type": "string",
      "description": "Destination CITY NAME, e.g. \"Tokyo\". Airport codes are not accepted."
    }
  }
}
    arguments 17 lines
  • flight_price_verdict reads unknown 9h ago

    Answers "buy now or wait?" for a route, from 90 days of observed prices: verdict, percentile of today's cheapest fare against its own history, median, all-time low, and sample size. This is not a flight search: it judges a price. No other public source computes it, because it needs the price history, not today's snapshot.

    mcp-tool

    {
  "type": "object",
  "required": [
    "origin",
    "destination"
  ],
  "properties": {
    "origin": {
      "type": "string",
      "description": "Origin CITY NAME, e.g. \"Milan\". Airport codes are not accepted."
    },
    "destination": {
      "type": "string",
      "description": "Destination CITY NAME, e.g. \"Tokyo\". Airport codes are not accepted."
    }
  }
}
    arguments 17 lines
  • when_to_book reads unknown never probed

    How many days before departure this route has historically been cheapest, from our own observations. Answers "am I booking too early or too late?".

    mcp-tool

    {
  "type": "object",
  "required": [
    "origin",
    "destination"
  ],
  "properties": {
    "origin": {
      "type": "string",
      "description": "Origin CITY NAME, e.g. \"Milan\". Airport codes are not accepted."
    },
    "destination": {
      "type": "string",
      "description": "Destination CITY NAME, e.g. \"Tokyo\". Airport codes are not accepted."
    }
  }
}
    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 f085782ebb2eb416.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f085782ebb2eb416/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/f085782ebb2eb416/badge.svg)](https://brick.blue/agent/f085782ebb2eb416?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
80%

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.