Get all exits from a room. Use look_at_surroundings for perception-filtered exits.
AI agents call get_room_exits to retrieve information from Rpg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves spatial navigation data from the game world without creating, modifying, or deleting any state. It has no destructive, financial, or execution implications—merely returning information about available exits in a room, consistent with typical read-only game engine queries.
From the tool's definition Tool name is 'get_room_exits' and description states 'Get all exits from a room.' This is a retrieval operation with no side effects. The description explicitly distinguishes it from perception filtering, indicating it queries game state without modification.
Documented attack patterns abuse exactly the kind of access get_room_exits gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rpg, and nothing reaches the server without passing your rules. This is the rule we recommend for get_room_exits:
{
"version": "1",
"default": "deny",
"tools": {
"get_room_exits": {}
}
}get_room_exits 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.
Get all exits from a room. Use look_at_surroundings for perception-filtered exits. It is categorised as a Read tool in the Rpg MCP Server, which means it retrieves data without modifying state.
Register the Rpg MCP server in PolicyLayer and add a rule for get_room_exits: 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 Rpg. Nothing to install.
get_room_exits 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_room_exits 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_room_exits. 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_room_exits is provided by the Rpg MCP server (mnehmos/mnehmos.rpg.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rpg, 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.
47 Rpg tools catalogued and risk-classified — across an index of 43,000+ MCP servers.