AI agents call check_cover to retrieve information from ChatRPG without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves game state information (cover mechanics) to inform game decisions. It is analogous to a 'get' or 'check' operation that queries existing data without changing anything. The read-only nature and limited scope within a game simulation context make misuse relatively low-risk.
From the tool's definition Tool description states it returns AC and Dex save bonuses—a purely informational query with no side effects. No state modification, deletion, code execution, or financial operations occur.
Attacks that exploit this kind of access
Check cover between attacker and target, returning AC and Dex save bonuses. It is categorised as a Read tool in the ChatRPG MCP Server, which means it retrieves data without modifying state.
Register the ChatRPG MCP server in PolicyLayer and add a rule for check_cover: 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 ChatRPG. Nothing to install.
check_cover 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 check_cover 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 check_cover. 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.
check_cover is provided by the ChatRPG MCP server (mnehmos/mnehmos.chatrpg.game). 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 →