AI agents call get_encounter to retrieve information from ChatRPG 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-only retrieval of encounter state data. It has no side effects—it simply fetches and returns existing combat state information in different detail levels. There is no creation, modification, deletion, or execution of actions. The blast radius of misuse is minimal, as incorrect queries would only return potentially irrelevant state information without affecting the encounter itself.
From the tool's definition Tool name is 'get_encounter' with description stating it retrieves 'the current state of a combat encounter' with various verbosity levels for output.
Attacks that exploit this kind of access
Get the current state of a combat encounter. Supports verbosity levels: minimal (LLM context), summary (quick overview), standard (default DM view), detailed (full state dump). It is categorised as a Read tool in the ChatRPG MCP Server, which means it retrieves data without modifying state.
Register the ChatRPG MCP server in PolicyLayer and add a rule for get_encounter: 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 ChatRPG. Nothing to install.
get_encounter 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_encounter 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_encounter. 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_encounter is provided by the ChatRPG MCP server (mnehmos/mnehmos.chatrpg.game). 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 →