_ registry / mcp streamable-http · checked 2h ago

united-starlink-tracker

https://unitedstarlinktracker.com

Registry code: 319163fc7c74b9a8

api record

United Airlines Starlink tracker. Scope: United Airlines. To change scope, append `?scope=ALL|HA|AS|QR` to the connector URL.

Fleet reality:

endpoint
https://unitedstarlinktracker.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 united-starlink-tracker live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is united-starlink-tracker free to use?
Yes — the hub reached it with no key and no payment.
What tools does united-starlink-tracker have?
7 tools: plan_starlink_itinerary, predict_flight_starlink, search_starlink_flights, predict_route_starlink, check_flight, list_starlink_aircraft, get_fleet_stats.
Is united-starlink-tracker 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 99%· all time 99%

latency
703ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 505 checks · signed record
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
used for
  • check if a flight has starlink
  • plan itinerary with starlink wifi
  • list starlink aircraft
  • get starlink fleet rollout stats
takes → gives
text → data
tools
7 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 7 tools
2 open 5 never probed 2 of 7 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_starlink_aircraft reads open 14h ago

    Use when the user asks about the planes themselves — "which tail numbers have Starlink?", "which aircraft types are equipped?". Returns United Airlines tail numbers, aircraft types, operators, and install dates (default 50 most recent; pass limit up to 500). Not for finding flights — use search_starlink_flights for that.

    mcp-tool

    {
      "type": "object",
      "examples": [
        {
          "fleet": "express",
          "limit": 100
        },
        {}
      ],
      "properties": {
        "fleet": {
          "enum": [
            "express",
            "mainline"
          ],
          "type": "string",
          "examples": [
            "express"
          ],
          "description": "Filter to only express (regional) or mainline aircraft."
        },
        "limit": {
          "type": "integer",
          "maximum": 500,
          "minimum": 1,
          "examples": [
            100
          ],
          "description": "Maximum number of aircraft to return (default 50)."
        }
      }
    }
    arguments 32 lines
  • get_fleet_stats reads open 14h ago

    Use when the user asks "how far along is the Starlink rollout?" or wants overall fleet numbers. Returns United Airlines Starlink installation counts and percentages across mainline and express fleets, plus a per-aircraft-type breakdown (installed/total per family). Not for per-flight checks — use check_flight for that.

    mcp-tool

    {
      "type": "object",
      "examples": [
        {}
      ],
      "properties": {}
    }
    arguments 7 lines
  • plan_starlink_itinerary reads unknown 5h ago

    Use when the user asks "what's the best way to fly X to Y with Starlink?" or wants ranked alternatives. PRIMARY TRAVEL-PLANNING TOOL — multi-stop search (up to 2 stops default, 3 max) ranked by COVERAGE RATIO (expected Starlink hours / total flight hours) so a 92% 1h direct scores the same as a 92% 10h multi-stop. Direct flights always shown first. Returns probability-ranked routings, NOT bookable itineraries — connection timing isn't validated; verify on the airline's site.

    mcp-tool

    {
      "type": "object",
      "examples": [
        {
          "origin": "SFO",
          "destination": "EWR"
        },
        {
          "date": "2026-05-20",
          "origin": "ORD",
          "max_stops": 1,
          "destination": "JAX"
        }
      ],
      "required": [
        "origin",
        "destination"
      ],
      "properties": {
        "date": {
          "type": "string",
          "examples": [
            "2026-05-20"
          ],
          "description": "Optional YYYY-MM-DD travel date. When within ~2 days (the aircraft-assignment window), uses confirmed tail assignments for higher accuracy. Beyond that, uses historical prediction only — confirmed assignments don't apply to future dates."
        },
        "origin": {
          "type": "string",
          "examples": [
            "SFO"
          ],
          "description": "Origin airport IATA code (e.g. 'SFO')."
        },
        "max_stops": {
          "type": "integer",
          "maximum": 3,
          "minimum": 0,
          "examples": [
            1
          ],
          "description": "Maximum number of connection stops (default 2, max 3). 0=direct only, 1=one connection, etc."
        },
        "destination": {
          "type": "string",
          "examples": [
            "JAX"
          ],
          "description": "Destination airport IATA code (e.g. 'JAX')."
        },
        "max_results": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "examples": [
            8
          ],
          "description": "Maximum number of itineraries with a Starlink-flown flight on every leg (default 8). Up to 3 partial baselines may be appended."
        }
      }
    }
    arguments 60 lines
  • predict_flight_starlink reads unknown 23h ago

    Use when the user asks "will my flight have Starlink?" for a date too far out for a confirmed assignment, or with no date at all. Returns the probability that a United Airlines flight number gets a Starlink plane, from historical observations. Reliability varies: high-confidence (5+ obs) is the most reliable tier but is not a guarantee; low-confidence (0-1 obs) is just the fleet prior. UA1-2999 (mainline) has materially lower coverage than UA3000-6999 (express) — call get_fleet_stats for the current split rather than assuming a rate.

    mcp-tool

    {
      "type": "object",
      "examples": [
        {
          "date": "2026-06-01",
          "flight_number": "UA544"
        },
        {
          "flight_number": "UA544"
        }
      ],
      "required": [
        "flight_number"
      ],
      "properties": {
        "date": {
          "type": "string",
          "examples": [
            "2026-06-01"
          ],
          "description": "Optional YYYY-MM-DD. ALWAYS PASS if known — the probability is date-agnostic, but when the result is low (<20%) the tool uses this date to look up the actual route and returns a ready-to-run plan_starlink_itinerary call with origin/dest pre-filled, so alternatives can be presented in one turn."
        },
        "flight_number": {
          "type": "string",
          "examples": [
            "UA544"
          ],
          "description": "Flight number, e.g. 'UA544' or just the digits. Also accepts operating-carrier codes like SKW5212, OO4680, UAL544."
        }
      }
    }
    arguments 31 lines
  • search_starlink_flights reads unknown 14h ago

    Use when the user asks "what Starlink flights leave from X tomorrow?" or wants scheduled near-term departures. Returns flights in the next ~2 days whose currently assigned aircraft is Starlink-equipped (verified or listed) — a published assignment, not a prediction, though an aircraft swap can still change it. Pass at least one of origin or destination (both narrows to a single route). Aircraft assignments aren't published further out, so for later dates use predict_route_starlink or plan_starlink_itinerary instead.

    mcp-tool

    {
      "type": "object",
      "examples": [
        {
          "origin": "ORD"
        },
        {
          "origin": "SFO",
          "destination": "EWR"
        }
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 100,
          "minimum": 1,
          "examples": [
            20
          ],
          "description": "Maximum number of flights to return (default 20)."
        },
        "origin": {
          "type": "string",
          "examples": [
            "ORD"
          ],
          "description": "Origin airport IATA code (e.g. 'SFO', 'ORD'). Case-insensitive."
        },
        "destination": {
          "type": "string",
          "examples": [
            "LAX"
          ],
          "description": "Destination airport IATA code (e.g. 'LAX', 'DEN'). Case-insensitive."
        }
      }
    }
    arguments 37 lines
  • predict_route_starlink reads unknown 5h ago

    Use when the user asks "which flights between X and Y have Starlink?" or "what Starlink flights serve airport X?". Single-route lookup: returns United Airlines flight numbers on a route (or touching an airport) ranked by Starlink probability. Pass both origin+destination for a specific route, OR just one to list all Starlink flights from/into an airport. For trip planning with connections, use plan_starlink_itinerary instead — this tool has no connection logic or coverage-ratio ranking. Empty result = route not served by Starlink planes.

    mcp-tool

    {
      "type": "object",
      "examples": [
        {
          "origin": "SFO",
          "destination": "EWR"
        },
        {
          "origin": "ORD"
        }
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 50,
          "minimum": 1,
          "examples": [
            10
          ],
          "description": "Maximum number of flight numbers to return (default 10)."
        },
        "origin": {
          "type": "string",
          "examples": [
            "SFO"
          ],
          "description": "Origin airport IATA code (e.g. 'SFO', 'ORD'). Case-insensitive."
        },
        "destination": {
          "type": "string",
          "examples": [
            "EWR"
          ],
          "description": "Destination airport IATA code (e.g. 'EWR', 'DEN'). Case-insensitive."
        }
      }
    }
    arguments 37 lines
  • check_flight reads unknown 5h ago

    Use when the user asks "does my flight have Starlink/WiFi?" with a specific United Airlines flight number and date. Returns YES if the published aircraft assignment is a plane verified to have Starlink, LIKELY YES if that plane is listed as Starlink-equipped but not yet verified, NO if it is a plane verified to have other WiFi, or a probability estimate if no assignment exists yet (assignments publish ~2 days out). An assignment can still change through an aircraft swap. For dates further out, call predict_flight_starlink directly — check_flight just falls through to the same estimate with extra latency.

    mcp-tool

    {
      "type": "object",
      "examples": [
        {
          "date": "2026-05-15",
          "flight_number": "UA544"
        }
      ],
      "required": [
        "flight_number",
        "date"
      ],
      "properties": {
        "date": {
          "type": "string",
          "examples": [
            "2026-05-15"
          ],
          "description": "Flight date in YYYY-MM-DD format, matched to the departure airport's local calendar date (UTC fallback for unmapped airports)."
        },
        "origin": {
          "type": "string",
          "description": "Optional 3-letter IATA departure airport of the traveller's leg (e.g. 'DEN'); scopes the answer to that leg of a multi-leg flight number."
        },
        "destination": {
          "type": "string",
          "description": "Optional 3-letter IATA arrival airport of the traveller's leg (e.g. 'SAN'); with origin, picks one leg of a multi-leg flight number."
        },
        "flight_number": {
          "type": "string",
          "examples": [
            "UA544",
            "544"
          ],
          "description": "Flight number, e.g. 'UA544' or just the digits. Also accepts operating-carrier codes like SKW5212, OO4680, UAL544."
        }
      }
    }
    arguments 38 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 319163fc7c74b9a8.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/319163fc7c74b9a8/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/319163fc7c74b9a8/badge.svg)](https://brick.blue/agent/319163fc7c74b9a8?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
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.