Get filtered room description accounting for darkness, fog, and perception. Returns exits and entities.
AI agents call look_at_surroundings 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 queries the game state to provide the player/agent with environmental information. It has no side effects on game data, entities, or mechanics. Even in a gaming context, retrieving room state is a safe read operation. Severity is low because misuse cannot cause game-breaking damage, financial loss, or irreversible changes.
From the tool's definition Tool description states it 'Get[s] filtered room description' and 'Returns exits and entities' — purely informational retrieval with no state modification. The verb 'look_at' and function of returning sensory data confirms read-only semantics.
Documented attack patterns abuse exactly the kind of access look_at_surroundings 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 look_at_surroundings:
{
"version": "1",
"default": "deny",
"tools": {
"look_at_surroundings": {}
}
}look_at_surroundings 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 filtered room description accounting for darkness, fog, and perception. Returns exits and entities. 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 look_at_surroundings: 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.
look_at_surroundings 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 look_at_surroundings 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 look_at_surroundings. 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.
look_at_surroundings 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.