Gracefully stop the Minecraft server. Uses RCON
AI agents invoke stop_server to trigger actions in Minecraft Server MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Stopping a server is an Execute action—it runs a remote command via RCON that causes an external system to perform an irreversible operational change (downtime, disconnection of all players). While not destructive to data, it disrupts service availability.
From the tool's definition Tool uses RCON to 'gracefully stop the Minecraft server,' which triggers an external operation (server shutdown) whose effects depend on execution timing and state.
Attacks that exploit this kind of access
Gracefully stop the Minecraft server. Uses RCON. It is categorised as a Execute tool in the Minecraft Server MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Minecraft Server MCP server in PolicyLayer and add a rule for stop_server: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Minecraft Server MCP. Nothing to install.
stop_server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop_server rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for stop_server. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
stop_server is provided by the Minecraft Server MCP server (tamo2918/minecraft-server-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →