Kick a player from the server with an optional reason.
AI agents invoke kick_player 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.
Kicking a player is an external operation that forcibly disconnects a player from the server. It is not purely destructive (the player can reconnect) nor a simple data write — it triggers an action on a live session. This fits Execute as it performs a stateful server operation affecting connected players, with medium severity since it disrupts player sessions but is reversible (player can rejoin).
From the tool's definition Kick a player from the server with an optional reason
Attacks that exploit this kind of access
Kick a player from the server with an optional reason. 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 kick_player: 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.
kick_player 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 kick_player 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 kick_player. 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.
kick_player 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 →