<\/p>\n
<\/center><\/p>\n
### **Keep your Minecraft server chat clean and safe with advanced AI technology!**
\nAI Chat Moderation is a powerful plugin that uses artificial intelligence to detect and filter harmful messages in your Minecraft server chat. With customizable detection categories and response actions, you can create a welcoming environment for all players.<\/p>\n
_The plugin uses an OPENAI or Mistral AI model, no API key required_<\/p>\n
## Features
\n– Advanced AI Detection: Identifies 12 categories of harmful content including harassment, hate speech, threats, violence, and inappropriate sexual content FOR all languages.
\n– Customizable Confidence Levels: Fine-tune detection sensitivity for each category
\n– Flexible Response System: Configure unique responses for different violation types
\n– Real-time Moderation: Option to check messages before or after they’re sent
\n– Comprehensive Logging: Track flagged messages in your server console
\n– Easy Configuration: Simple YAML file with detailed options<\/p>\n
## Installation
\nJust drag and drop the plugin jar into your plugins folder and it is ready !
\nNo need to create an OPENAI key. To not to leave any doubt, message may be cached in my programs for performance purpose only.<\/p>\n
## How It Works
\nThe plugin analyzes each chat message using AI technology to determine if it contains harmful content. When potentially harmful content is detected, the plugin can:<\/p>\n
– Hide the message from other players
\n– Send warning messages to the offending player
\n– Execute custom commands based on the violation type
\n– Kick or take other administrative actions for severe violations<\/p>\n
Give your moderators the tools they need to maintain a positive community without constantly monitoring chat. AI Chat Moderation works silently in the background, allowing you to focus on building and playing while keeping your server safe for everyone.<\/p>\n
## Commands
\n– \/acm reload : To reload the plugin
\n– \/acm debug : To see the categories confidence of each message sent. It allows to adjust your categories confidence easily.<\/p>\n
## Permissions
\n– acm.reload : To be able to use \/acm reload
\n– acm.debug : To be able to use \/acm debug
\n– acm.bypass : To bypass the checks (**By default OP bypass**)<\/p>\n
_AI Chat Moderation – Smart protection for your Minecraft community_<\/p>\n
The configuration file:
\n“`yaml
\n# Enable or disable the plugin
\nenabled: true<\/p>\n
# —- NO AI PART —-
\n# To blacklist some words without using AI
\nblacklisted-words:
\n – fuck you
\n – retarded
\n# Whether or not the message will be hidden when it contains a blacklisted word
\nblacklisted-words-hide-message: true
\n# The commands to run if the message contains a blacklisted word
\nblacklisted-words-commands:
\n – “SEND_MESSAGE &6%player% &cUse a correct language.”<\/p>\n
# —- AI PART —-
\n# Choose your provider OPENAI or MISTRAL or DETOXIFY
\n# + Mistral is better for arabic and Russian languages
\n# + OpenAI responses are faster
\n# + Detoxify Very fast, good for IT, FR, RU, PT, ES, TR but not very detection when the insult is splitted \/ not well written \/ acronym<\/p>\n
providers: [DETOXIFY, OPENAI]
\n# True: the plugin will log the flagged messages in the console
\n# False: the plugin will not log the flagged messages in the console
\nlogs-flagged-messages: true
\nlogged-message-format: “Flagged message: Player:[%player%] – Message:[%message%] – Category:[%category%] – Confidence[%confidence%]”
\n# True: the plugin will check the message before it is sent (the message will be a bit delayed, approximately 0.3s)
\n# False: the plugin will check the message after it has been sent (the message will not be delayed) but if the message is flagged, the message will not be deleted
\ncheck-after-message-has-been-sent: false
\n# The different harmful categories that the plugin can detect
\ncategories:
\n # OPENAI
\n illicit\/violent:
\n # True: the plugin will detect the messages in this category
\n # False: the plugin will not detect the messages in this category
\n detection: true
\n # The actions that the plugin will do when a message is detected in this category
\n actions:
\n warn:
\n # Adjust the confidence level to detect the messages in this category
\n # When it is higher the plugin will detect only the messages with height intensity of harmfulness
\n # When it is lower the plugin will detect the messages with low intensity of harmfulness
\n # From 0.0 to 1.0, 0.85 is a good value
\n confidence: 0.80
\n # Whether the plugin will hide the message from the player
\n hideMessage: true
\n # The commands that the plugin will execute when a message is detected in this category
\n # Placeholders: %player%: the player who sent the message
\n # %player_uuid%: the UUID of the player who sent the message
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use violent language.”
\n other:
\n confidence: 0.95
\n hideMessage: true
\n commands:
\n – “kick %player%”
\n # OPENAI
\n self-harm\/instructions:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use self-harm instructions.”
\n # OPENAI
\n harassment:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to harass other players.”
\n # OPENAI
\n violence\/graphic:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use violence.”
\n # OPENAI
\n illicit:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use illicit language.”
\n # OPENAI
\n self-harm\/intent:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use self-harm intent.”
\n # OPENAI
\n hate\/threatening:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use threatening language.”
\n # OPENAI
\n sexual\/minors:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use sexual language.”
\n # OPENAI
\n harassment\/threatening:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use threatening language.”
\n # OPENAI
\n hate:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use hate language.”
\n # OPENAI
\n self-harm:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use self-harm language.”
\n # OPENAI and MISTRAL
\n sexual:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use sexual language.”
\n # OPENAI
\n violence:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use violent language.”
\n # MISTRAL
\n # Content that expresses prejudice, hostility, or advocates discrimination against individuals or groups based on protected characteristics such as race, ethnicity, religion, gender, sexual orientation, or disability. This includes slurs, dehumanizing language, calls for exclusion or harm targeted at specific groups, and persistent harassment or bullying of individuals based on these characteristics.
\n hate_and_discrimination:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use hate language.”
\n # MISTRAL
\n # Content that describes, glorifies, incites, or threatens physical violence against individuals or groups. This includes graphic depictions of injury or death, explicit threats of harm, and instructions for carrying out violent acts. This category covers both targeted threats and general promotion or glorification of violence.
\n violence_and_threats:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use violent language.”
\n # MISTRAL
\n # Content that promotes or provides instructions for illegal activities or extremely hazardous behaviors that pose a significant risk of physical harm, death, or legal consequences. This includes guidance on creating weapons or explosives, encouragement of extreme risk-taking behaviors, and promotion of non-violent crimes such as fraud, theft, or drug trafficking.
\n dangerous_and_criminal_content:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use violent language.”
\n # MISTRAL
\n # Content that promotes, instructs, plans, or encourages deliberate self-injury, suicide, eating disorders, or other self-destructive behaviors. This includes detailed methods, glorification, statements of intent, dangerous challenges, and related slang terms
\n selfharm:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use violent language.”
\n # MISTRAL
\n # Content that contains or tries to elicit detailed or tailored medical advice
\n health:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use tailored medical language.”
\n # MISTRAL
\n # Content that contains or tries to elicit detailed or tailored financial advice.
\n financial:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use financial language.”
\n # MISTRAL
\n # Content that contains or tries to elicit detailed or tailored legal advice.
\n law:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use elicit detailed language.”
\n # MISTRAL
\n # Content that requests, shares, or attempts to elicit personal identifying information such as full names, addresses, phone numbers, social security numbers, or financial account details.
\n pii:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to leak personal information.”
\n # DETOXIFY
\n toxicity:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use toxic language.”
\n # DETOXIFY
\n sexual_explicit:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use sexual explicit language.”
\n # DETOXIFY
\n severe_toxicity:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use severe toxic language.”
\n # DETOXIFY
\n obscene:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use obscene language.”
\n # DETOXIFY
\n threat:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use threat language.”
\n # DETOXIFY
\n identity_attack:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use threat language.”<\/p>\n
# DETOXIFY
\n insult:
\n detection: true
\n actions:
\n warn:
\n confidence: 0.80
\n hideMessage: true
\n commands:
\n – “SEND_MESSAGE &6%player% &cYou are not allowed to use insult language.”<\/p>\n
print-api-errors: false # For debugging purposes, I advice you to set it to false in production
\n“`<\/p>\n","protected":false},"excerpt":{"rendered":"
AI-Powered Chat Moderation Plugin, Prevent your players to send harmful content.<\/p>\n","protected":false},"featured_media":9497,"template":"","meta":{"_minecraft_slug":"ai-chat-moderation","_minecraft_project_id":"C0RvmsiN","_minecraft_author":"Ssomar","_minecraft_license":"LicenseRef-All-Rights-Reserved","_minecraft_downloads":2932,"_minecraft_follows":20,"_minecraft_client_side":"unsupported","_minecraft_server_side":"required","_minecraft_storage_type":"zip","_minecraft_archive_name":"ai-chat-moderation.zip","_minecraft_size_bytes":4060599,"_minecraft_version_count":65,"_minecraft_updated_at":"2026-05-16T05:14:30.570480Z","_minecraft_date_created":"2025-03-31T16:08:02.995664Z","_minecraft_date_modified":"2025-10-16T21:15:47.191818Z","_minecraft_project_url":"https:\/\/modrinth.com\/mod\/ai-chat-moderation","_minecraft_icon_attachment_id":9497,"_minecraft_imported_at":"2026-05-31T15:40:37+00:00","_minecraft_import_hash":"16d876be32aba2b701eb0a5834e42ec6","_minecraft_versions":"","_minecraft_links":"","_minecraft_gallery":"","_minecraft_api_metadata":""},"mod_category":[124,894,125,126,127,128,867,129,123,92,992],"mod_loader":[130,895,131,132,133,134,993],"minecraft_version":[339,340,341,357,359,360,379,382,385,438,446,449,110,111,112,113,114,115,116,117,118,119,120,46,47,48,49,50,51,52,53,54,55,56,57,58,59,36,60,93,94,101,102,62,37,40,73,74,38,78,79,80,81,82,22,23,24,25,26,27,28,29,30,31,860,861,862,863,864],"class_list":["post-9496","mod","type-mod","status-publish","has-post-thumbnail","hentry","mod_category-bukkit","mod_category-bungeecord","mod_category-folia","mod_category-management","mod_category-paper","mod_category-purpur","mod_category-social","mod_category-spigot","mod_category-technology","mod_category-utility","mod_category-waterfall","mod_loader-bukkit","mod_loader-bungeecord","mod_loader-folia","mod_loader-paper","mod_loader-purpur","mod_loader-spigot","mod_loader-waterfall","minecraft_version-1-10","minecraft_version-1-10-1","minecraft_version-1-10-2","minecraft_version-1-11","minecraft_version-1-11-1","minecraft_version-1-11-2","minecraft_version-1-12","minecraft_version-1-12-1","minecraft_version-1-12-2","minecraft_version-1-13","minecraft_version-1-13-1","minecraft_version-1-13-2","minecraft_version-1-14","minecraft_version-1-14-1","minecraft_version-1-14-2","minecraft_version-1-14-3","minecraft_version-1-14-4","minecraft_version-1-15","minecraft_version-1-15-1","minecraft_version-1-15-2","minecraft_version-1-16","minecraft_version-1-16-1","minecraft_version-1-16-2","minecraft_version-1-16-3","minecraft_version-1-16-4","minecraft_version-1-16-5","minecraft_version-1-17","minecraft_version-1-17-1","minecraft_version-1-18","minecraft_version-1-18-1","minecraft_version-1-18-2","minecraft_version-1-19","minecraft_version-1-19-1","minecraft_version-1-19-2","minecraft_version-1-19-3","minecraft_version-1-19-4","minecraft_version-1-20","minecraft_version-1-20-1","minecraft_version-1-20-2","minecraft_version-1-20-3","minecraft_version-1-20-4","minecraft_version-1-20-5","minecraft_version-1-20-6","minecraft_version-1-21","minecraft_version-1-21-1","minecraft_version-1-21-10","minecraft_version-1-21-2","minecraft_version-1-21-3","minecraft_version-1-21-4","minecraft_version-1-21-5","minecraft_version-1-21-6","minecraft_version-1-21-7","minecraft_version-1-21-8","minecraft_version-1-21-9","minecraft_version-1-8","minecraft_version-1-8-1","minecraft_version-1-8-2","minecraft_version-1-8-3","minecraft_version-1-8-4","minecraft_version-1-8-5","minecraft_version-1-8-6","minecraft_version-1-8-7","minecraft_version-1-8-8","minecraft_version-1-8-9","minecraft_version-1-9","minecraft_version-1-9-1","minecraft_version-1-9-2","minecraft_version-1-9-3","minecraft_version-1-9-4"],"yoast_head":"\n