CALL THIS FIRST when player wants to play. Returns existing games (most recent first) or instructs to start new game if none exist.
AI agents call get_game_menu to retrieve information from DMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing game data to the player without modifying, deleting, or executing any operations. It is purely informational—listing games and providing instructions. This is a classic Read operation with no side effects, warranting low severity.
From the tool's definition Tool description states it 'Returns existing games' and 'instructs' users. The verb 'Returns' and the read-only nature of retrieving and displaying game state indicate no data modification, deletion, or code execution.
Documented attack patterns abuse exactly the kind of access get_game_menu gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_game_menu:
{
"version": "1",
"default": "deny",
"tools": {
"get_game_menu": {}
}
}get_game_menu is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
CALL THIS FIRST when player wants to play. Returns existing games (most recent first) or instructs to start new game if none exist. It is categorised as a Read tool in the DMCP MCP Server, which means it retrieves data without modifying state.
Register the D MCP server in PolicyLayer and add a rule for get_game_menu: 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 DMCP. Nothing to install.
get_game_menu 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_menu 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_menu. 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_menu is provided by the D MCP server (shawnrushefsky/dmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
204 DMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.