AI agents call load_game 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 data (an existing game session) by ID. The verb 'load' combined with the description indicates a read-only retrieval operation. There is no indication that it modifies game state, executes external operations, deletes data, or involves financial transactions. It is a straightforward data retrieval tool typical of game session management systems.
From the tool's definition Tool name is 'load_game' and description states 'Load an existing game by ID' — this retrieves or queries an existing game state from storage by identifier, with no modification of data or side effects beyond reading.
Documented attack patterns abuse exactly the kind of access load_game 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 load_game:
{
"version": "1",
"default": "deny",
"tools": {
"load_game": {}
}
}load_game 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.
Load an existing game by ID. 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 load_game: 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.
load_game 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 load_game 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 load_game. 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.
load_game 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.