Moderator Bot
3,380 serversAbout Moderator Bot
Moderator Bot Features
Moderator Bot is free anti-NSFW protection, captcha verification, and advanced multimodal AI moderation.
View more at https://modbot.neomechanical.com.
NSFW Scanning
Classify posted images and media into categories such as Sexual, Violence Graphic, Self Harm, Self Harm Intent, and Self Harm Instructions.
Supports GIFs, emojis, stickers, images and videos.
Pick from the following to auto-trigger on detection: Delete Message, Strike, Timeout, Kick, Ban, Warn User, Give / Remove / Temporary Role.
NSFW Text Moderation
Classify plain text and OCR from images into categories such as Sexual, Violence, Sexual Content Involving Minors, Harassment, Harassment (Threatening), Hate, Hate (Violent), Self Harm variants, Illicit, and Illicit (Violent).
Same actions as scanning above; optional strikes-only mode and excluded channels.
Scan Avatars
NSFW profile pictures: configurable DM, then Kick, Ban, Timeout, or other enforcement you select.
AI Moderation
Get AI to monitor chat and detect users violating your server rules and decide the best punishment for rule breakers. (delete, strike, timeout, kick, ban, warn, roles, etc).
Voice Moderation
Transcribe selected voice channels; run your rules on the transcript with outcomes in the same strike / timeout / kick / ban / delete family you configure.
Scam Protection
Phishing links, scam imagery, and related detections—route each hit to delete, strike, kick, ban, timeout, or logging per rule.
Supports text and images, such as crypto scams.
Security Screening
Captcha, anti-vpn, anti-alt, join verification with logs and records of discovered alt accounts and VPN users.
Strike Policies
Warn, timeout, kick, ban, stacking strikes, cooldowns, and where automation hands off to a human.
Banned Words
Word and phrase lists; optional OCR on images.
Per match: the usual message and member actions (delete, strike, timeout, kick, ban, warn, roles).
Banned URLs
URL and domain patterns; on match, same action choices as above.
Review queue
Items wait for a moderator to approve, reject, or adjust before the bot finalizes.
Monitor Feed
Log moderation triggers, joins, and all events related to the bot, including simple events such as message edits.
Strike Management
View and edit strike counts and history per member.
Whitelist
Roles exempt from chosen automations.
Support Tickets
Simple ticket system with AI integration to handle support tickets with information you provide to the AI.
FAQ Responses
The AI replies to commonly asked questions with responses you set.
Announcements
Schedule announcements to channels.
Member Dashboard
Member self-service to look at strikes/violations and other stats.
Moderation Metrics
Stats on the number of NSFW scans and flagged content, as well as moderation speed.
Profiles
Smart insights into your users and the risk they pose to your community.
Bot Branding
Custom display name and avatar for the bot in your server.
Popular Commands
| Command | Description |
|---|---|
/channels | Configure log channels. setSet a log channel. unsetUnset a log channel. showShow current log channel settings. |
/bannedurls | Banned URLs management commands. addAdd a URL or domain to the banned list. removeRemove a URL or domain from the banned list. listList all banned URLs. clearClear all banned URLs. add_actionAdd a moderation action to be triggered when a banned URL is detected. remove_actionRemove a specific action from the list of punishments for banned URLs. view_actionsShow all actions currently configured to trigger when banned URLs are used. |
/bannedwords | Banned words management commands. profilesShow available built-in banned word profiles. importImport a built-in banned word profile. addAdd a word to the banned words list. removeRemove a word from the banned words list. listList all banned words. clearClear all banned words. set_match_ruleConfigure how banned words are matched. reset_match_ruleReset global or per-word banned word matching rules. view_match_rulesView banned word matching rules. set_sourcesSet which sources are scanned for banned words. view_sourcesView which sources are scanned for banned words. add_actionAdd a moderation action to be triggered when a banned word is detected. remove_actionRemove a specific action from the list of punishments for banned words. view_actionsShow all actions currently configured to trigger when banned words are used. |
/help | Get help on settings. commandOptional: command group to get help with dumpDump 100% of command docs as files. |
/strikes | Strike management commands. getGet strikes of a specific user. clearClear all strikes of a specific user. add_actionAdd an additional action for a strike level. remove_actionRemove an action from a strike level. view_actionsView all configured strike actions. |
Categories
Tags
Monetization
Languages
Links
Similar Bots
Other moderation and tools bots you might like
Popular on UpBot
Trending bots in our directory