Skip to content
SecureKy
NL EN
Dashboard Add bot

AI Moderator · local on EU servers

Toxic chat? You set the bar, SecureKy acts

Detect swearing and toxic messages on our servers in Europe, the same check as in Discord. You choose how strict; OpenRouter is optional for the whole platform.

  1. Detect Spot toxic tone
  2. Score Confidence + language
  3. Act Delete or warn
Enable in the panel Try the demo

How SecureKy acts · local on EU servers

In SecureKy

What you control, what SecureKy does

No generic benefit grid: this is how the module fits your panel.

01

On our servers

By default the check runs on our servers. No third-party AI for scam images or default AI moderation.

Pick a point or let the preview rotate.

Live check

Same classifier as in Discord

Type a test message and pick Mild, Normal or Strict. You see score, labels and whether the bot would act.

  • Same strictness options as the dashboard
  • Scored only, not stored
  • Max 10 tests per minute
Toxicity score:
Scored only, not stored, not shared. Max 10 tests per minute

Pipeline & panel

From score to action

How the check works and which strictness/actions you set in the panel.

01

Local tone check

Local tone check (or optional OpenRouter) for how toxic a message sounds.

Click through the pipeline and thresholds.

Get started

Enable in the panel

Three steps in panel.secureky.eu. No setup commands in Discord.

Dashboard Add bot

FAQ

FAQ

Privacy, demo vs Discord, languages and cost, short and factual.

01

Do messages go to OpenAI or Google?

Not for the default check on our servers, and not for scam image scans. OpenRouter is an explicit choice; then only the text for the check goes to that AI. The demo follows the same choice.

PrivacyOpen panel

Ready to try

Enable AI Moderator on your server

Invite, open the dashboard, pick how strict, and test above whether it fits your community.

Add bot Dashboard