How it works

Six signals. One transparent score.

Every message that hits MxGuard is checked against six independent signals running in parallel. Their combined output is a single transparent score from 0.0 (definitely clean) to 1.0 (definitely spam).

01

Machine learning model

LightGBM gradient-boosted classifier trained on 34,000 labelled examples. Returns a probability 0.0–1.0 for each message in under 3 milliseconds.

02

URL reputation

Every URL in the message body checked against Spamhaus DBL and SURBL — the canonical block lists used by industry-leading mail security.

03

Sender reputation

Rolling 7-day spam/ham ratio per sender domain, cached in Redis. Repeat offenders score higher; trusted senders score lower.

04

Attachment scanning

ClamAV virus scanning. Risk scoring for password-protected archives, executable files, macro-enabled documents, and other suspicious types.

05

Threat feed match

URLhaus active-malicious-URL feed from abuse.ch, refreshed every 6 hours. Catches phishing and malware campaigns within hours of first detection.

06

Heuristic signals

Reverse DNS, gibberish-detection, suspicious TLDs, freemail-to-role patterns. VERP-aware so legitimate bulk mailers like Mailchimp aren't penalised.

Combined score determines verdict:

< 0.50 — deliver clean
0.50–0.75 — tag [SPAM]
0.75–0.97 — quarantine
≥ 0.97 — reject at SMTP

Setup

Protected in three steps.

From sign-up to live mail filtering: typically 10 minutes plus DNS propagation.

01

Add your domain

From your dashboard, enter the domain and the hostname of your real mail server (where clean mail should land). Done in 30 seconds.

02

Verify ownership

Add a single TXT record to your DNS. Click verify. We confirm via DNS lookup and flip the domain to active.

03

Point your MX

Update your MX records to mx1.mxguard.uk. Mail begins flowing through MxGuard within minutes.