AdvancedSensitiveWords
github.com
- Self-hosted
What AdvancedSensitiveWords is
AdvancedSensitiveWords is a free, open-source moderation plugin for Minecraft servers running Paper. It uses DFA word matching and event-based inspection 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 actions such as commands, damage, effects, hostile behavior and shadowbans. Version 2.x targets Paper 1.21.11 and requires Java 21; Spigot, CraftBukkit and BungeeCord are unsupported. Installation involves downloading a Paper artifact from a release or building it locally, then placing it in the server plugins directory. Optional LLM chat review is off by default and reviews messages that pass the DFA and chat-context checks. It requires a compatible provider and API key, and stores request and response audits locally as sensitive operational data. An optional Velocity module supports notifications and proxy commands but does not filter chat on its own. Other Paper plugins can use its shadowban API, and the plugin emits an asynchronous moderation response event after an LLM response. It is licensed under GNU AGPL-3.0.
Who it suits
It is for Minecraft server operators running Paper who need configurable content moderation. Operators considering LLM review should also be prepared to manage a provider, API key and sensitive local audit data.
Good to know, and what to watch
- Checks chat, commands, signs and item text.
- Matched content can be replaced or canceled.
- Supports configurable moderation actions including shadowbans.
- Optional LLM review is disabled by default.
- Other Paper plugins can use its shadowban API.
- Version 2.x requires Paper 1.21.11 and Java 21.
- Spigot, CraftBukkit and BungeeCord are unsupported.
- Velocity does not filter chat by itself.
- LLM audit data is stored locally as sensitive data.
The verdict
AdvancedSensitiveWords gives Paper operators configurable checks and responses, with optional AI review and integrations. Confirm the server version and Java requirement, and account for the sensitivity of locally stored LLM audit records.
What the maker publishes
- 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. source
- AI review
- Optional LLM chat review is disabled by default and can review messages that pass the DFA and chat-context checks. source
- AI safeguards
- LLM review applies message-length, entropy, cooldown, concurrency, and queue limits, and locally parses model output before follow-up actions. source
- API
- Other Paper plugins can use its shadowban API, and it fires an asynchronous moderation response event after an LLM response. source
- Compatibility limit
- Since version 2.x, Spigot, CraftBukkit, and BungeeCord are unsupported. source
- Content filters
- It checks chat, commands, writable books, signs, anvil results, item names and lore, player names, and optionally broadcasts. source
- Content filters
- It can check chat, commands, books, signs, anvils, item names and lore, player names, and broadcasts. source
- Distribution
- The README instructs users to download the Paper artifact from a release or build paper:shadowJar locally. source
- Installation
- The Paper artifact can be downloaded from a release or built locally, then placed in the server plugins directory. source
- Integrations
- Optional integrations listed include Velocity, TrChat, PacketEvents, PlaceholderAPI, Floodgate, and AuthMe. source
- Integrations
- The README lists compatibility with TrChat, optional PacketEvents, PlaceholderAPI, Floodgate, and AuthMe. source
- 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. source
- License
- The project states that it is licensed under GNU AGPL-3.0. source
- License
- The project is licensed under GNU AGPL-3.0. source
- LLM providers
- The configuration supports CHAT_COMPLETIONS, RESPONSES, or ANTHROPIC_MESSAGES API modes and gives DeepSeek as an example base URL. source
- Maker identity
- The repository is published under GitHub account HaHaWTH, whose profile displays the name Creeam HaHaWTH. source
- Moderation actions
- Matched content can be replaced or canceled, and configured actions include commands, damage, effects, hostile behavior, and shadowbans. source
- Moderation actions
- Matched content can be replaced or cancelled, and configured violation levels can trigger actions such as commands, damage, effects, or shadowbans. source
- 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. source
- 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. source
- Platform limit
- Version 2.x targets Paper only; the README says Spigot, CraftBukkit, and BungeeCord are unsupported. source
- Proxy limitation
- The Velocity module supports notifications and proxy commands but does not filter chat on its own. source
- Proxy module
- The optional Velocity module supports notifications and proxy commands but does not filter chat by itself. source
- Purpose
- AdvancedSensitiveWords is a Paper moderation plugin using DFA word matching, event-based content inspection, modular violation levels, and optional LLM-assisted chat review. source
Checked against the maker's pages on 4 Oct 2026.