AI agents call mc_check_connection to retrieve information from Mc Rcon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only status check with no side effects. It retrieves information about the RCON connection but does not execute commands, modify data, or trigger external operations. The minimal information disclosure and lack of actionable impact on the server classify this as a low-severity read operation.
From the tool's definition Tool name 'mc_check_connection' and description 'Check RCON connection status' indicate a query/diagnostic operation that retrieves connection state without modifying or executing actions on the server.
Attacks that exploit this kind of access
Check RCON connection status. It is categorised as a Read tool in the Mc Rcon MCP Server, which means it retrieves data without modifying state.
Register the Mc Rcon MCP server in PolicyLayer and add a rule for mc_check_connection: 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_check_connection 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 mc_check_connection 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_check_connection. 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_check_connection 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 →