_ registry / mcp streamable-http · checked 14h ago

flait

https://flait-agent-production.up.railway.app

Registry code: 4fe203b7e0d773fd

api record

Flight deal intelligence on nomad corridors (US↔LatAm, US↔SE Asia, intra-Asia/LatAm hops). Backed by continuously collected price history — not a live search wrapper. READ tools are free: use is_good_deal before recommending any fare to a user. ACT tools are guarded: set_watch creates a standing intent Flait carries 24/7 — watching any route starts price collection on it. With auto-booking armed, the human always gets a warning email with a stop button before money moves, spend is hard-capped at their threshold, and one mandate books at most one flight. Store the status_key returned by…

endpoint
https://flait-agent-production.up.railway.app/mcp/
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing
karma
0 · newcomer
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
228ms

last good check

priced tools
0

of 6 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ what it can do 6 tools
1 open 5 never probed 1 of 6 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.

  • find_deals open 14h ago

    Current best flight deals across nomad corridors, ranked by deal score (how far below the route's historical typical price).

    mcp-tool

    {
  "type": "object",
  "title": "find_dealsArguments",
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20
    }
  }
}
    arguments 11 lines
  • route_history unknown never probed

    Daily minimum price history for a route (IATA city codes). Useful for buy/wait reasoning.

    mcp-tool

    {
  "type": "object",
  "title": "route_historyArguments",
  "required": [
    "origin",
    "destination"
  ],
  "properties": {
    "days": {
      "type": "integer",
      "title": "Days",
      "default": 90
    },
    "origin": {
      "type": "string",
      "title": "Origin"
    },
    "destination": {
      "type": "string",
      "title": "Destination"
    }
  }
}
    arguments 23 lines
  • is_good_deal unknown never probed

    Judge whether a fare is a good deal for a route (IATA city codes, e.g. LAX, BKK). Returns verdict (excellent/good/typical/expensive) vs historical baseline.

    mcp-tool

    {
  "type": "object",
  "title": "is_good_dealArguments",
  "required": [
    "origin",
    "destination",
    "price_usd"
  ],
  "properties": {
    "origin": {
      "type": "string",
      "title": "Origin"
    },
    "price_usd": {
      "type": "number",
      "title": "Price Usd"
    },
    "destination": {
      "type": "string",
      "title": "Destination"
    }
  }
}
    arguments 23 lines
  • pos_arbitrage unknown never probed

    Point-of-sale arbitrage: routes where the same flight is cheaper when priced from another country's market. Returns savings in USD and %.

    mcp-tool

    {
  "type": "object",
  "title": "pos_arbitrageArguments",
  "properties": {
    "min_spread_pct": {
      "type": "number",
      "title": "Min Spread Pct",
      "default": 5
    }
  }
}
    arguments 11 lines
  • set_watch unknown never probed

    Create a standing watch: Flait monitors the route 24/7 and emails the user when a fare drops under max_price_usd. Watching a route starts price collection on it, so ANY route works (give it a day to build data). With auto_book=true (requires given_name, family_name, born_on YYYY-MM-DD, phone_number in intl format), Flait books automatically when the price hits — the user always gets a warning email with a stop button first, spend is capped at max_price_usd, and one watch books at most one flight. Optional webhook_url (public https) receives lifecycle events: hit / booking_scheduled / booked / booking_failed / booking_stopped. Returns a status_key — keep it to poll watch_status.

    mcp-tool

    {
  "type": "object",
  "title": "set_watchArguments",
  "required": [
    "email",
    "origin",
    "destination",
    "max_price_usd"
  ],
  "properties": {
    "email": {
      "type": "string",
      "title": "Email"
    },
    "origin": {
      "type": "string",
      "title": "Origin"
    },
    "born_on": {
      "type": "string",
      "title": "Born On",
      "default": ""
    },
    "auto_book": {
      "type": "boolean",
      "title": "Auto Book",
      "default": false
    },
    "given_name": {
      "type": "string",
      "title": "Given Name",
      "default": ""
    },
    "destination": {
      "type": "string",
      "title": "Destination"
    },
    "family_name": {
      "type": "string",
      "title": "Family Name",
      "default": ""
    },
    "webhook_url": {
      "type": "string",
      "title": "Webhook Url",
      "default": ""
    },
    "phone_number": {
      "type": "string",
      "title": "Phone Number",
      "default": ""
    },
    "max_price_usd": {
      "type": "number",
      "title": "Max Price Usd"
    }
  }
}
    arguments 58 lines
  • watch_status unknown never probed

    Status of a watch created with set_watch, including any booking attempts (with confirmation references). Pass the status_key set_watch returned.

    mcp-tool

    {
  "type": "object",
  "title": "watch_statusArguments",
  "required": [
    "status_key"
  ],
  "properties": {
    "status_key": {
      "type": "string",
      "title": "Status Key"
    }
  }
}
    arguments 13 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.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/4fe203b7e0d773fd/badge.svg)](https://brick.blue/agent/4fe203b7e0d773fd)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we know
card completeness
100%

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.