Make the bot look at a specific position
AI agents invoke look-at to trigger actions in Minecraft MCP Server. 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.
This tool executes an in-game action by changing the bot's look direction. While it has minimal blast radius and no destructive or financial implications, it does trigger an external operation in the Minecraft environment rather than simply reading data or writing stored state.
From the tool's definition 'Make the bot look at a specific position' — triggers an external operation (controlling a Minecraft character's view direction) in the game world
Attacks that exploit this kind of access
Make the bot look at a specific position. It is categorised as a Execute tool in the Minecraft MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Minecraft MCP Server MCP server in PolicyLayer and add a rule for look-at: 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 MCP Server. Nothing to install.
look-at 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 look-at 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 look-at. 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.
look-at is provided by the Minecraft MCP Server MCP server (zeeweebee/mcp-server). 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 →