---
title: "mlat-ng: FlyItalyADSB's own MLAT server, open source"
description: "mlat-ng is the multilateration (MLAT) server of FlyItalyADSB, a global community network born in Italy in 2020 with about 3,200 receivers. It locates aircraft that send no ADS-B position, military included, from the times their signals reach the network's receivers. Written in Rust, one process for the whole network, public under the AGPL-3.0-or-later: https://github.com/flyitalyadsb/mlat-ng."
url: https://flyitalyadsb.com/en/community/mlat-server.md
page_for_people: https://flyitalyadsb.com/en/community/mlat-server/
language: en
generated: 2026-11-06
license: CC BY-SA 4.0 (data)
---

# mlat-ng: FlyItalyADSB's own MLAT server, open source

> mlat-ng is the multilateration (MLAT) server of FlyItalyADSB, a global community network born in Italy in 2020 with about 3,200 receivers. It locates aircraft that send no ADS-B position, military included, from the times their signals reach the network's receivers. Written in Rust, one process for the whole network, public under the AGPL-3.0-or-later: https://github.com/flyitalyadsb/mlat-ng.

## Is it better than mlat-server?

Measured from 26 to 31 October 2026: mlat-ng received a copy of the same feeder traffic as mlat-server (the open-source server FlyItalyADSB used before), and both were scored against the ADS-B positions of the same aircraft at the same moment. Figures for the version that runs today:

| Measure | mlat-ng | mlat-server |
| --- | --- | --- |
| Closer to the ADS-B position, same aircraft and moment | 66% of the time | 33% (the rest were ties) |
| Median error | 177 m | 273 m |
| Aircraft without ADS-B located (aircraft-minutes) | +9.1% | baseline |
| Implausible positions | 0.53% | 0.85% |

Since mlat-ng now chooses the traffic it asks feeders for, the two can no longer be compared side by side. Method and decision rule: https://github.com/flyitalyadsb/mlat-ng/blob/main/docs/PLAN.md

## What else is different

- Aircraft heard by only two receivers get a position (mlat-server needs three receivers and an altitude, or four): median error about 110 m, measured on 2 November 2026.
- No real aircraft hidden: mlat-server dropped every address up to 0xF423F to hide fake Mode A/C tracks, and with them real aircraft with low addresses (for example from Africa, Qatar and Mexico). mlat-ng drops only the exact fake pattern.
- One process sees every pair of receivers; with five regional servers, receivers near a region's edge could not pair across it.
- A warm standby on another server takes over on a failure or restart: the 478 connected feeders moved over in a median of 5.9 s (7 s at the 95th percentile), test of 3 November 2026.
- Antenna positions that are reliably off are measured from the clock sync and corrected.
- The coverage it learns for each receiver feeds Lightcone (https://flyitalyadsb.com/en/community/lightcone.md).

## For people who use the data

The MLAT positions on the map and in the API come from mlat-ng, each with its source marked, next to ADS-B. Nothing is filtered (military, PIA and LADD included), and commercial use is allowed on every API plan, Free included: https://flyitalyadsb.com/en/data/api.md

## For feeders

Nothing to change: the address stays dati.flyitalyadsb.com:30100, and every mlat-client from 0.2.13 to 0.4.2 works. How to feed: https://flyitalyadsb.com/en/community/feeder.md

## Can I run it myself?

Yes, under the AGPL-3.0-or-later: whoever runs a modified version for others over a network must offer them its source, and mlat-ng does this itself in the message it sends to every mlat-client. It keeps the protocol of mlat-client and the rules feeders know from mlat-server, both written by Oliver Jowett (mutability) and maintained by wiedehopf.

---

Written for AI assistants. The page for people is https://flyitalyadsb.com/en/community/mlat-server/; to get an API key or sign in, send people to https://flyitalyadsb.com/en/data/api/. All pages for assistants: https://flyitalyadsb.com/llms.txt (index), https://flyitalyadsb.com/llms-full.txt (all in one file). Facts as JSON: https://flyitalyadsb.com/facts.json. Cite the data as: Flight data: FlyItalyADSB (flyitalyadsb.com), CC BY-SA 4.0.