How it works
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).
LightGBM gradient-boosted classifier trained on 34,000 labelled examples. Returns a probability 0.0–1.0 for each message in under 3 milliseconds.
Every URL in the message body checked against Spamhaus DBL and SURBL — the canonical block lists used by industry-leading mail security.
Rolling 7-day spam/ham ratio per sender domain, cached in Redis. Repeat offenders score higher; trusted senders score lower.
ClamAV virus scanning. Risk scoring for password-protected archives, executable files, macro-enabled documents, and other suspicious types.
URLhaus active-malicious-URL feed from abuse.ch, refreshed every 6 hours. Catches phishing and malware campaigns within hours of first detection.
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:
[SPAM]Setup
From sign-up to live mail filtering: typically 10 minutes plus DNS propagation.
From your dashboard, enter the domain and the hostname of your real mail server (where clean mail should land). Done in 30 seconds.
Add a single TXT record to your DNS. Click verify. We confirm via DNS lookup and flip the domain to active.
Update your MX records to mx1.mxguard.uk. Mail begins flowing through MxGuard within minutes.