Documentation

Everything you need to set up and configure Nexvor on your Minecraft server

🚀

Quick Setup

Get started in 5 minutes

⚙️

Configuration

Customize AI behavior

🔧

Troubleshooting

Common issues & fixes

🚀 Quick Setup Guide

1. Download & Install

  1. Download the plugin from your dashboard (paid tiers) or download page (BASIC tier)
  2. Place nexvor-1.0.0.jar in your server's /plugins folder
  3. Restart your Minecraft server (not just reload)
  4. Check console for "[Nexvor] Plugin enabled successfully"

2. Add Your License Key (MEDIUM/MAX only)

If you purchased MEDIUM or MAX, you'll need to activate your license:

  1. Open plugins/Nexvor/config.yml
  2. Find the license-key: field
  3. Paste your license key (format: TIER-UUID-SIGNATURE)
  4. Save the file and run /nexvor reload

Note: BASIC tier doesn't require a license key. Leave it blank or set to "NONE".

3. Configure AI Provider

Choose your AI provider and add your API key:

OpenAI (GPT-4, GPT-3.5)

ai-provider: "openai"
api-keys:
  openai: "sk-proj-xxxxxxxxxxxxx"
model: "gpt-4o-mini"  # or gpt-4, gpt-3.5-turbo

Get your API key from platform.openai.com

Anthropic (Claude)

ai-provider: "anthropic"
api-keys:
  anthropic: "sk-ant-xxxxxxxxxxxxx"
model: "claude-3-5-sonnet-20241022"

Get your API key from console.anthropic.com

Groq (Fast & Free)

ai-provider: "groq"
api-keys:
  groq: "gsk_xxxxxxxxxxxxx"
model: "llama-3.1-70b-versatile"

Get your API key from console.groq.com (free tier available)

Ollama (Self-Hosted)

ai-provider: "ollama"
ollama-url: "http://localhost:11434"
model: "llama3.2"

Install Ollama from ollama.ai and run ollama pull llama3.2

4. Test It Out

  1. Run /nexvor reload to apply changes
  2. Type in chat: Hey AI, how are you?
  3. The AI should respond within a few seconds
  4. Use /nexvor status to check plugin health

⚙️ Configuration Reference

Basic Settings

prefix:

Chat prefix to trigger AI (default: none, responds to all chat)

prefix: "ai"  # Players type: ai hello
response-delay:

Minimum delay between responses in seconds (prevents spam)

response-delay: 3
max-context-messages:

Number of recent messages to remember (MEDIUM/MAX only)

max-context-messages: 20

Personality Customization (MAX only)

system-prompt:

Define AI's personality and behavior

system-prompt: |
  You are a friendly medieval wizard living in a Minecraft server.
  You speak with wisdom and humor, occasionally making references to
  magic spells and potions. Keep responses under 100 words.

Advanced Settings

temperature:

Response creativity (0.0 = focused, 1.0 = creative)

temperature: 0.8
max-tokens:

Maximum response length

max-tokens: 150
timeout-seconds:

API request timeout

timeout-seconds: 30

🔧 Troubleshooting

❌ "License key invalid" error

Causes:

  • License key was copied incorrectly (missing characters)
  • Using BASIC tier but trying to activate a license
  • License has been refunded or revoked
  • Server has already been activated on 3 other servers (limit reached)

Solutions:

  • Double-check your license key from the email or dashboard
  • Deactivate an old server from your dashboard
  • Contact [email protected] if issue persists

⚠️ AI not responding to chat

Causes:

  • API key is invalid or missing
  • API quota exceeded (out of credits)
  • Wrong model name in config
  • Network/firewall blocking API requests

Solutions:

  • Check console for error messages
  • Verify API key is correct and has credits
  • Test with a different model (e.g., gpt-4o-mini is cheaper)
  • Ensure server can reach external APIs (check firewall)

🐌 Responses are very slow

Causes:

  • Using a slow/large model (e.g., gpt-4)
  • High API latency
  • max-tokens set too high

Solutions:

  • Switch to faster models: gpt-4o-mini, groq/llama-3.1-70b-versatile
  • Reduce max-tokens to 100-150
  • Use Groq for near-instant responses (free tier available)

💡 Best Practices

  • Start with BASIC tier to test, upgrade if you need more features
  • Use Groq for free, fast responses during testing
  • Set response-delay to 3-5 seconds to prevent spam
  • Keep max-tokens under 200 for quick responses
  • Use system-prompt to set boundaries (e.g., "Keep responses under 50 words")
  • Monitor your API usage to avoid unexpected charges
  • Regularly check for plugin updates

📋 Commands Reference

/nexvor reload

Reload configuration without restarting server

/nexvor status

Check plugin health and license status

/nexvor version

Display plugin version and tier

/nexvor clear

Clear conversation context (MEDIUM/MAX only)

Still Need Help?

We're here to help you get Nexvor running smoothly

Contact Support