Find the nearest block of a specific type
AI agents call find-block to retrieve information from Minecraft MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the Minecraft world to locate blocks of a specified type and return their position. It is a read-only operation with no side effects—no blocks are modified, deleted, or interacted with. The action is purely informational retrieval, consistent with the Read category (search, list, get, fetch). Low severity because misuse simply returns block coordinates with no harmful consequences.
From the tool's definition Tool name 'find-block' and description 'Find the nearest block of a specific type' indicate a search/query operation that retrieves information about block locations without modifying game state.
Attacks that exploit this kind of access
Find the nearest block of a specific type. It is categorised as a Read tool in the Minecraft MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Minecraft MCP Server MCP server in PolicyLayer and add a rule for find-block: 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.
find-block is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the find-block 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 find-block. 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.
find-block 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 →