Skip to content
SPECIFICTION
Get listed

AdvancedSensitiveWords

github.com

Self-hosted
Visit github.com
Spec score 7.5 #6 of 19 in Minecraft Moderation Plugins

What it is

AdvancedSensitiveWords is a free, open-source moderation plugin for operators of Minecraft servers running Paper. It inspects content through DFA word matching and event-based checks across chat, commands, writable books, signs, anvil results, item names and lore, player names, and optionally broadcasts. Operators can replace or cancel matched content and configure responses such as commands, damage, effects, hostile behavior, or shadowbans. Version 2.x targets Paper 1.21.11 and requires Java 21; installation involves placing a released or locally built Paper artifact in the server’s plugins directory. Optional LLM chat review is off by default and uses a compatible provider and API key to assess messages missed by the other checks. Length, entropy, cooldown, concurrency, and queue safeguards apply. Requests and responses are recorded locally in an llm-history directory identified as sensitive operational data. Optional integrations include Velocity, TrChat, PacketEvents, PlaceholderAPI, Floodgate, and AuthMe. Velocity support handles notifications and proxy commands, not chat filtering. The project is licensed under GNU AGPL-3.0.

Spec sheet

Purpose
AdvancedSensitiveWords is a Paper moderation plugin using DFA word matching, event-based content inspection, modular violation levels, and optional LLM-assisted chat review.Read 4 Oct 2026 · github.com
Intended users
Installation and configuration instructions describe placing the plugin on a Paper server and setting its server-side configuration, indicating it is for Minecraft server operators.Read 4 Oct 2026 · github.com
API
Other Paper plugins can use its shadowban API, and it fires an asynchronous moderation response event after an LLM response.Read 4 Oct 2026 · github.com
Integrations
The README lists compatibility with TrChat, optional PacketEvents, PlaceholderAPI, Floodgate, and AuthMe.Read 4 Oct 2026 · github.com
License
The project is licensed under GNU AGPL-3.0.Read 4 Oct 2026 · github.com
AI privacy handling
LLM requests and responses are audited in a local llm-history directory that the README says to treat as sensitive operational data.Read 4 Oct 2026 · github.com
AI review
Optional LLM chat review is disabled by default and can review messages that pass the DFA and chat-context checks.Read 4 Oct 2026 · github.com
AI safeguards
LLM review applies message-length, entropy, cooldown, concurrency, and queue limits, and locally parses model output before follow-up actions.Read 4 Oct 2026 · github.com
Compatibility limit
Since version 2.x, Spigot, CraftBukkit, and BungeeCord are unsupported.Read 4 Oct 2026 · github.com
Content filters
It can check chat, commands, books, signs, anvils, item names and lore, player names, and broadcasts.Read 4 Oct 2026 · github.com
Distribution
The README instructs users to download the Paper artifact from a release or build paper:shadowJar locally.Read 4 Oct 2026 · github.com
Installation
The Paper artifact can be downloaded from a release or built locally, then placed in the server plugins directory.Read 4 Oct 2026 · github.com
LLM providers
The configuration supports CHAT_COMPLETIONS, RESPONSES, or ANTHROPIC_MESSAGES API modes and gives DeepSeek as an example base URL.Read 4 Oct 2026 · github.com
Maker identity
The repository is published under GitHub account HaHaWTH, whose profile displays the name Creeam HaHaWTH.Read 4 Oct 2026 · github.com
Moderation actions
Matched content can be replaced or cancelled, and configured violation levels can trigger actions such as commands, damage, effects, or shadowbans.Read 4 Oct 2026 · github.com
Operational data
LLM requests and responses are audited in the plugin's llm-history directory, which the README says to treat as sensitive operational data.Read 4 Oct 2026 · github.com
Optional AI review
LLM chat review is disabled by default, uses a compatible provider and API key, and only reviews messages missed by DFA and chat-context checks.Read 4 Oct 2026 · github.com
Platform limit
Version 2.x targets Paper only; the README says Spigot, CraftBukkit, and BungeeCord are unsupported.Read 4 Oct 2026 · github.com
Proxy limitation
The Velocity module supports notifications and proxy commands but does not filter chat on its own.Read 4 Oct 2026 · github.com
Proxy module
The optional Velocity module supports notifications and proxy commands but does not filter chat by itself.Read 4 Oct 2026 · github.com
Supported server
Version 2.x targets Paper 1.21.11 and requires Java 21.Read 4 Oct 2026 · github.com
Word matching
The plugin uses DFA word matching and event-based content inspection.Read 4 Oct 2026 · github.com

Strong points and limits

Strong points

  • Checks chat, commands, books, signs, and item details.
  • Matched content can be replaced or canceled.
  • Optional LLM review has queue and concurrency safeguards.
  • Other Paper plugins can use the shadowban API.

Limits

  • Version 2.x requires Paper 1.21.11 and Java 21.
  • Spigot, CraftBukkit, and BungeeCord are unsupported.
  • LLM request and response audits are stored locally as sensitive data.
  • Velocity support does not filter chat by itself.

Who it suits

It suits Minecraft server operators who need configurable moderation on Paper. Operators should note that version 2.x excludes Spigot, CraftBukkit, and BungeeCord.

Verdict

AdvancedSensitiveWords offers Paper operators a broad set of content checks and configurable moderation responses. Its optional LLM review and integrations add flexibility, while its Paper-only compatibility and locally retained AI audit data are important operational considerations.

Where Specifiction places it

Alternatives to AdvancedSensitiveWordsAll alternatives →