Server Assistant

Most Discord mod bots just react to messages.
This one understands your whole community.

Discord and Minecraft, moderated as one place · AutoMod that learns your team · fair ban appeals · a tamper-proof audit trail.

Add to Discord Explore every feature

⛏️ Download the MCDC plugin 🃏 Crestbound

Free to start. The full moderation toolkit is free forever.

Trusted by

What makes Server Assistant different

Most bots are rule-runners: a message breaks a filter, the bot reacts. Server Assistant runs your whole community, Discord and Minecraft together, with an intelligence layer on top.

⛏️

Minecraft + Discord, one community Free on every plan

MCDC bridges your Minecraft server and Discord into a single place: players chat across both worlds as themselves, with their real name and skin avatar, and your moderation follows them everywhere.

Two-way chat, plus live server health in Discord: TPS, RAM, uptime, and who's online.
Playtime earns XP into the same balance as Discord activity.
Moderation on every surface players write on: chat, signs, books, anvils, name tags, private messages.
Web ban appeals, even for bans Server Assistant didn't issue.
One-click account linking and a self-updating plugin.

Locked down by design: outbound HTTPS only, no RCON, no open ports, and no admin credentials ever leave your server.

⬇ Download the plugin (v0.30.0) Read the bridge guide →

FernGully#minecraft · from the server

anyone up for the nether run tonight?

Server AssistantApp#minecraft

🟢 Server health

Online

7 players · FernGully, Pixel_Petra, +5

Performance

20.0 TPS · RAM 48% · up 6d 4h

Two-way bridge · shared XP · every surface moderated

🛡️

ThreatNet Free tier on by default

Our cross-server threat network: a raider or scammer with a serious, corroborated history on other protected servers lights up on yours before they strike. Advisory by default, and severity-only: never the offence, the reasons, or which server acted.

How it works

Servers contribute minimized, pseudonymous signals: counts, recency, and a generic severity level. The advisory band is free for every server; Premium adds the richer cross-server view and opt-in auto-protect at a threshold you choose. Individuals can opt out of profiling in the web portal, subject to a published safety exception; a Premium auto-protect ban is silent and stays contestable via the portal.

🛎️

Reception Free

A branded verification front desk for new joiners, with a free auto-generated banner in your server's colours, a quick are-you-human check, and a self-healing honeypot that catches bots which post instead of verifying.

How it works

New members land at the Reception desk and tap Verify me; passing grants the verified role, and most automated raid bots never make it past the door. Premium adds an AI concierge that greets and helps newcomers at the desk.

✨

SAi, your AI assistant In-game: Premium

The same assistant across Discord and Minecraft. In game, @sai answers grounded in the real Minecraft wiki, with clickable citations, and a personal Allay companion answers privately at your side.

How it works

In the web portal, SAi reads your server's setup and applies improvements in one tap. In game (Premium), answers cite their minecraft.wiki sources so players can check them, and each server can give SAi its own persona: name, tone, attitude.

🔏

A mod toolkit that can't be tampered with Free

Every action, even hand-made bans, lands in an encrypted audit log staff can't edit or erase, with the owner alerted if anyone tries. Anti-nuke guards the server itself, and the full moderation toolkit is free forever.

What's in the box

Warn / mute / kick / ban / tempban with tiered approval and 24-hour undo, AutoMod with an AI second-opinion that learns your team's judgment, anti-raid and lockdown, fair ban appeals with one-tap staff decisions, alt detection, and whole-server health digests. See every feature.

🧾

Honest AI budgeting No surprises

A clear AI allowance, a plain-English usage breakdown of where every token went, and simple top-up packs when you want more. No meters you can't read, no invisible burn.

How it works

Check your balance any time, see usage split by feature in plain words, and top up only if you choose to. Word-filter AI checks run on a free moderation endpoint and never touch your allowance. Details on Pricing.

What your staff actually sees

The same intelligence, in the moments it matters. Each panel is a to-scale mock of a real message: the situation on one side, what the bot does on the other.

A regular suddenly turns hostile in #general

Third flare-up with the same member today. Instead of guessing, a moderator right-clicks the message → Message Report.

What the feature does

Message Report reads ~20 surrounding messages and returns a 3 to 5 bullet AI summary (tone, likely rule broken, escalation pattern, suggested action) with one-tap Warn / Timeout / Kick / Ban. The bot never auto-acts; staff always decide, and the action is logged with the report attached.

Server AssistantAppright-click → Message Report

Message Report

• Tone: hostile, escalating
• Likely breaks: rule 3, personal attacks
• Pattern: third flare-up with the same member today
• Suggested: short timeout + a staff check-in

AI summary · reads ~20 messages of context

WarnTimeoutKickBan

A day-old account drops a "free Nitro" link

Classic scam, posted while your team is asleep. AutoMod handles it before anyone sees it, and tells the user why.

What the feature does

Filter packs catch scams / slurs (IP-grabber domains preloaded); the message is removed and the user DM'd which rule fired plus their warning count. Staff are completely exempt, and repeat hits auto-escalate up your punishment ladder.

Server AssistantApp#staff-log

AutoMod · scam_link

User

@newbie_4821 · account 19h old

Action

Message deleted · auto-warning #1 · user DM'd

join for free nitro discord-gift[.]ru/x

Logged · staff exempt · IP-grabbers preloaded

A mod tries to purge 200 messages

Powerful, irreversible, so it doesn't just run. The action routes up the chain for sign-off, and everything is logged.

What the feature does

Tiered approval: dangerous actions (like /purge) post an approval card to a higher tier. Only the Owner can approve an Admin's request. Once approved it executes and is written to your audit trail with the approver recorded. No rogue purges, no silent mass-deletes.

Server AssistantApp#staff-log

Approval needed: /purge 200

@admin-jess wants to purge 200 messages in #general. This routes up a tier for sign-off.

Requested by

@admin-jess (Admin)

Approver

Owner only

ApproveDeny

Recently shipped · New features ship continuously, see the changelog for the latest · full changelog →

The complete toolkit

Everything below is in the box. The free tier is a complete moderation suite; Premium adds your server's own power tools.

Full mod toolkit

warn · mute · kick · ban · softban · /tempban (timed, auto-unban) · one-command /role · tiered approval (dangerous actions route up the chain) · 24-hour undo.

AutoMod engine

Filter packs (scams / slurs), custom regex with a safety check, link blocklist, anti-spam, and an auto-escalating punishment ladder. Staff are completely exempt.

Anti-raid & lockdown

Always-on mass-join detection with staff alerts. /lockdown locks every channel in one command and restores the exact prior permissions when lifted.

Reception verification

An in-server Reception welcome desk with a Verify-me button and a quick human check, stopping most automated raid bots cold before they reach your channels.

Ticket Panels

Private in-server support tickets: a panel button opens a private channel with an intake form; a .txt transcript is saved on close. The bot can even create the channel for you.

AI extras

/imagine image generation · /translate · /faq Q&A · right-click Message Report & Translate. Use the host's key or bring your own.

Customisation Hub

Sub-wizards in /settings: branding, role tiers, punishment ladders, notifications and more. Everything saves instantly, no code. (Pulse lives in the web portal, not here.)

Premium toolkit

Reaction roles · custom /commands with live embeds · AI Q&A from your FAQ · translation · AI mediator · backup & restore · white-label branding. Most set up from a one-screen wizard.

Three ways to use it

Slash commands, anywhere

Every action works as a / command in any channel: /warn, /mute, /ban, /tempban, /lockdown, /purge…

Text, in staff-chat

Natural-language shorthand: warn @user, mute @user 30 min, purge since 1pm.

Right-click menus

Apps ▸ View Info / View Warnings on a user, or Message Report on a message for an AI summary.

Coming up next · Your votes decide: feature polls land in your staff chat and the top picks ship first · see the live roadmap →

Add to Discord Explore every feature

Server Assistant · Features · Crestbound Vision · Compare · Pricing · Roadmap · Support