AI agents call get-command-results 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 a read operation that queries historical command results. While it operates within a game environment with other destructive capabilities (launch-nuke, move-fleet, place-structure), get-command-results itself has no side effects—it only retrieves data. The blast radius is minimal since an AI agent misusing this tool cannot cause game state changes, only access information about past actions.
From the tool's definition Tool retrieves results of previously executed commands by their correlation IDs using a query-based interface ("Retrieves the results"). No data creation, modification, or deletion occurs; it purely fetches information about command outcomes.
Attacks that exploit this kind of access
Retrieves the results of previously executed commands by their correlation IDs. Use this to check results when skipVerification=true was used. 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-command-results: 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-command-results 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-command-results 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-command-results. 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-command-results 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 →