AI agents call get-game-state to retrieve information from Defcon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only retrieval of game state data. While the server overall contains dangerous capabilities (launch-nuke, move-fleet, place-structure), this specific tool only queries information without creating, modifying, or deleting anything. It has no destructive or operational impact on its own.
From the tool's definition Tool name is 'get-game-state' and description states it 'Retrieves the latest game state information'. The verb 'retrieves' and the absence of any modification language indicate this is a data query with no side effects.
Attacks that exploit this kind of access
Retrieves the latest game state information. It is categorised as a Read tool in the Defcon MCP Server, which means it retrieves data without modifying state.
Register the Defcon MCP server in PolicyLayer and add a rule for get-game-state: 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 Defcon. Nothing to install.
get-game-state 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 get-game-state 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 get-game-state. 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.
get-game-state is provided by the Defcon MCP server (jorisvddonk/defcon-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 →