AI agents use place-fleet to create or update resources in Defcon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Defcon environment.
This tool creates/places game entities (fleet of ships) at specified coordinates within the DEFCON game. It is a Write operation as it modifies the game state by adding a fleet, but it is reversible in the sense that fleets can be moved or destroyed later. While it operates within a game simulation, misuse could lead to unintended in-game consequences, hence medium severity.
From the tool's definition Places a fleet of ships at the specified coordinates. You can specify up to 6 ships.
Attacks that exploit this kind of access
Places a fleet of ships at the specified coordinates. You can specify up to 6 ships. IMPORTANT: Check the response to verify if placement was successful!. It is categorised as a Write tool in the Defcon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Defcon MCP server in PolicyLayer and add a rule for place-fleet: 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.
place-fleet 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 place-fleet 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 place-fleet. 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.
place-fleet 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 →