Minecraft

This MCP server provides a Python-based FastMCP implementation to control a Minecraft server via RCON. It exposes a toolset and resources that allow you to issue Minecraft commands programmatically, query the available commands, and interact with the in-game world through an LLM-powered interface. The server uses a local STDIO setup for development and can be extended to HTTP/SSE for production deployments. Use the included mcp_chat_client to listen for in-game chat directed at the AI (messages starting with @ai) and have those requests translated into server commands via Gemini integration. To start, run the server script in a Python virtual environment, then launch the chat client in a separate terminal if you want conversational control via chat.

Prerequisites:

• Python 3.8+ installed on your system
• Virtual environment support (venv) available
• Minecraft server with RCON enabled (server.properties: enable-rcon=true, rcon.password=<password>, rcon.port=<port>)

Installation steps:

1. Clone the repository and navigate to the mcp_server directory:

cd Minecraft-MCP-Server/mcp_server

2. Create and activate a virtual environment:

python -m venv venv
# Windows
venv\Scripts\activate
# Unix/macOS
source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

4. Create a .env file with required configuration (examples):

MINECRAFT_LOG_PATH=/path/to/minecraft/logs/latest.log
MCP_SERVER_PATH=mcp_server/server.py
GEMINI_API_KEY=your_gemini_api_key

5. Run the MCP server:

python mcp_server/server.py

6. (Optional) Run the chat client in a separate terminal after starting the server:

venv\Scripts\activate  # Windows
# or: source venv/bin/activate  # Unix
python mcp_server/mcp_chat_client.py

Notes:

• Ensure the Minecraft server is running and accessible via RCON before starting the MCP server.
• The project uses a local STDIO transport by default for development and can be extended to HTTP/SSE in production.

Tips and common issues:

• Memory overflow bug: If the chat client is started before the MCP server, you may encounter memory issues. Always start the server first, then launch the chat client.
• Ensure your RCON settings in server.properties match the credentials used by the MCP server (port and password).
• The commands and tools are exposed via commands.json and the FastMCP integration, enabling dynamic command discovery and execution.
• When deploying in production, consider transitioning to HTTP/SSE transport and Docker for isolation, as suggested in the readme's Next Steps.
• If you modify environment paths, update the PATH in the mcp_config.env accordingly to ensure Python and dependencies are found.