AI agents use mc_whitelist_add to create or update resources in Mc Rcon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mc Rcon environment.
This tool creates or modifies server whitelist entries by adding players. While it modifies server state, the action is reversible (players can be removed via mc_whitelist_remove). It does not execute arbitrary commands (which would be Execute), delete data (Destructive), or involve financial transactions.
From the tool's definition Tool name 'mc_whitelist_add' and description 'Add a player to the server whitelist' indicate creation/modification of whitelist data.
Attacks that exploit this kind of access
Add a player to the server whitelist. It is categorised as a Write tool in the Mc Rcon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mc Rcon MCP server in PolicyLayer and add a rule for mc_whitelist_add: 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 Mc Rcon. Nothing to install.
mc_whitelist_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mc_whitelist_add 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 mc_whitelist_add. 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.
mc_whitelist_add is provided by the Mc Rcon MCP server (pedxyuyuko/mc-rcon-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 →