minecraft-rcon-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_MODEL | No | Anthropic model for in-game chat. | claude-sonnet-4-5 |
| LOG_PATH | No | Path to the server log to tail. Set this explicitly — the default is relative to the working directory. | ./logs/latest.log |
| AI_PREFIX | No | Chat trigger prefix (case-insensitive). | ai |
| RCON_HOST | No | RCON host | localhost |
| RCON_PORT | No | RCON port | 25575 |
| AI_MAX_TOKENS | No | Max tokens per chat response. | 1024 |
| RCON_PASSWORD | No | RCON password (match server.properties) | changeme |
| AI_MAX_CONTEXT | No | Exchanges retained in the rolling history. | 10 |
| AI_CHAT_ENABLED | No | Set 0/false to run a pure RCON tool server (no log tailing, no Anthropic usage). | 1 |
| AI_SYSTEM_PROMPT | No | Replace the entire system prompt. | |
| ANTHROPIC_API_KEY | No | Required for in-game AI chat. | |
| AI_SYSTEM_PROMPT_EXTRA | No | Append server-specific context (Minecraft version, house rules) to the default prompt. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_commandA | Run a Minecraft server command via RCON and return the response. Examples: 'list', 'data get entity @e[type=minecraft:cat,limit=5,sort=nearest]', 'locate structure village', 'execute at @p run data get block ~ ~ ~' |
| get_ai_chat_statusA | Return the status of the in-game AI chat listener and conversation history. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools, get_ai_chat_status and run_command, have clear and distinct purposes. One retrieves chat status, the other executes arbitrary commands, leaving no ambiguity.
Both tool names follow a consistent verb_noun pattern (get_ai_chat_status, run_command), making them predictable and easy to differentiate.
With only 2 tools, the server is minimally functional. While run_command covers core RCON operations, the additional AI chat tool is specific; the count is low but acceptable for a narrow purpose.
The server provides basic RCON command execution and AI chat status, but lacks tools for managing AI chat (e.g., enable/disable) or more granular server interactions, leaving notable gaps.