MCP Server - Connect AI to FlightLabs - Real-Time Flight Tracker & Status API. Live data for flights, airports, schedules, timetables, IATA codes, and more.
MCP ready

MCP Server, connect AI to live flight data

Integrate FlightLabs with Claude Desktop, ChatGPT or any MCP-compatible assistant. Query live flights, schedules, delays, prices, airlines, routes, and airports in your AI conversations.

Ask Claude:

"Where is flight AA217 right now?"

AI calls MCP tool:
{
"tool": "flights.realtime",
"params": {
"flightIata": "AA217"
}
}

What is MCP and why does it matter?

The Model Context Protocol (MCP) lets AI assistants access external data in real time. Instead of outdated training data, your AI can fetch live flight data from FlightLabs — just by asking a question.

Example: Ask Claude "Where is flight AA217 right now?" and it will call our flights.realtime tool automatically.

Real-time flights

Live positions, status, airline and airport filters via /flights.

Natural language

Ask questions like "Show American Airlines flights departing JFK" and get accurate answers.

Same API quota

MCP calls use your existing FlightLabs plan. Each AI request counts as one API call.

Available MCP tools

Ten tools mapped to core FlightLabs REST endpoints. Pass access_key on every call.

flights.realtime Flights

Get real-time flight positions and status. Filter by flight IATA/ICAO, airline, departure or arrival airport, registration, and more. Maps to GET /flights.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

flights.historical Flights

Historical departures or arrivals for an airport by date or date range. Maps to GET /historical.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

flights.prices Flights

Search flight prices between airports (oneway or roundtrip). Maps to GET /retrieveFlights.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

flights.delays Flights

Find delayed flights above a minimum delay threshold. Maps to GET /flight_delays.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

flights.schedules Flights

Airport timetable of scheduled departures or arrivals. Maps to GET /advanced-flights-schedules.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

flights.by_number Flights

Flight info by flight number (e.g. LH811), optionally for a date or range. Maps to GET /flight.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

flights.by_airline Flights

Live flights operated by a given airline ICAO code. Maps to GET /flights-by-airline.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

airlines.list Airlines

Airline directory with optional IATA or country filter. Maps to GET /airlines.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

airlines.routes Airlines

Airline routes between airports, filterable by airline or flight. Maps to GET /routes.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

airports.by_filter Airports

Look up airports by IATA, ICAO, city, or country code. Maps to GET /airports-by-filter.

Useful params: flightIata, airlineIata, depIata, arrIata, limit, and more.

Getting started

Connect in minutes using your API key in the endpoint URL. For direct programmatic calls, include access_key in the tool arguments.

MCP endpoint

Start your free trial to get your API key, then replace YOUR_ACCESS_KEY above.

Connect to Claude Desktop

Add this configuration to your Claude Desktop config file. On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json
{
  "mcpServers": {
    "goflightlabs": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.goflightlabs.com/mcp?access_key=YOUR_ACCESS_KEY"
      ]
    }
  }
}

Start your free trial to get your API key and replace YOUR_ACCESS_KEY in the configuration above.

After setup, try asking Claude: "Where is flight AA217 right now?"

OpenAI proxy — use with ChatGPT

Our OpenAI-compatible proxy enriches ChatGPT responses with real-time flight data. Send your request to our endpoint instead of OpenAI's and we'll inject live data into the AI context.

How it works:
  1. You send a request to our proxy with your OpenAI API key in the Authorization header
  2. We fetch real-time flight data using the MCP tool you specify
  3. We inject the data into the conversation context
  4. OpenAI responds with accurate, up-to-date information
curl — track AA217 via OpenAI proxy
curl -X POST "https://mcp.goflightlabs.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_OPENAI_API_KEY" \
  -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Where is flight AA217 right now?"}],"force_mcp_tool":{"tool_name":"flights.realtime","params":{"access_key":"YOUR_ACCESS_KEY","flightIata":"AA217"}}}'
Parameters:
  • Authorization: Bearer … — your OpenAI API key (header only; never put it in the body)
  • model — any OpenAI model (gpt-4o-mini, gpt-4o, etc.)
  • force_mcp_tool.tool_name — use flights.realtime
  • force_mcp_tool.params.access_key — your FlightLabs access key
  • force_mcp_tool.params.flightIata — e.g. AA217 (or other filters like airlineIata, depIata)

Python: track a flight example

A complete Python example that fetches real-time data for flight AA217 using the MCP protocol.

get_flight_ba179.py
import httpx
import json
import asyncio

MCP_SERVER_URL = "https://mcp.goflightlabs.com/mcp"
ACCESS_KEY = "YOUR_ACCESS_KEY"

async def call_mcp_tool(tool_name: str, arguments: dict):
    async with httpx.AsyncClient(timeout=60) as client:
        init_response = await client.post(
            MCP_SERVER_URL,
            json={
                "jsonrpc": "2.0",
                "id": "1",
                "method": "initialize",
                "params": {
                    "protocolVersion": "2024-11-05",
                    "capabilities": {},
                    "clientInfo": {"name": "PythonClient"}
                }
            }
        )
        session_id = init_response.headers.get("Mcp-Session-Id")

        response = await client.post(
            MCP_SERVER_URL,
            headers={"Mcp-Session-Id": session_id},
            json={
                "jsonrpc": "2.0",
                "id": "2",
                "method": "tools/call",
                "params": {
                    "name": tool_name,
                    "arguments": {"access_key": ACCESS_KEY, **arguments}
                }
            }
        )
        return response.json()

async def main():
    result = await call_mcp_tool(
        "flights.realtime",
        {"flightIata": "AA217"}
    )
    print(json.dumps(result, indent=2))

asyncio.run(main())

Connect ChatGPT to real-time flight data

Use FlightLabs MCP to give ChatGPT access to live flight positions and status.

Step 1: Get your API key

Start your free trial and generate your FlightLabs access key.

Step 2: Add MCP connector in ChatGPT

Paste this MCP endpoint:

Step 3: Ask for live data

  • "Where is flight AA217 right now?"
  • "Show American Airlines flights departing JFK"
  • "List live flights arriving at LAX"
  • "What is the status of flight AA100?"

Ready to integrate? Get your API key in minutes.

Get started

Frequently asked questions

An API key is required to use these tools. Start your free trial to get access. Check our pricing page for plan details. Pass the key as access_key in the tool arguments (same as the REST API).
MCP requests count toward your existing API quota just like REST API calls. Each tool call equals one API request. Check our pricing page for plan details.
Ten tools cover real-time flights, historical data, prices, delays, schedules, flight-by-number, flights-by-airline, airlines, routes, and airports-by-filter. See Available Tools above for the full list and REST mappings.
Yes! Any platform that supports the Model Context Protocol (MCP) specification can connect to our server. This includes Claude Desktop, custom Python clients, ChatGPT connectors, and any future MCP-compatible platforms.