AI agents invoke set-submarine-state to trigger actions in Defcon. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool issues a command to change the operational state of a submarine within the DEFCON game, which is an external operation that triggers game state changes. While it includes potentially launching nukes, this is all within a game simulation context. The action is an Execute-category command that triggers external game operations depending on the chosen state argument.
From the tool's definition Sets the state of a submarine (passive sonar, active sonar, or nuke)
Attacks that exploit this kind of access
Sets the state of a submarine (passive sonar, active sonar, or nuke). It is categorised as a Execute tool in the Defcon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Defcon MCP server in PolicyLayer and add a rule for set-submarine-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.
set-submarine-state is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the set-submarine-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 set-submarine-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.
set-submarine-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 →