End the current combat encounter.
AI agents use end_encounter to create or update resources in Rpg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rpg environment.
The tool modifies game state by concluding a combat encounter, which affects persistence in the SQLite backend. While reversible (not destructive), it clearly writes/modifies data rather than reading it. The medium severity reflects that misuse would disrupt a tabletop session but cannot cause data loss or irreversible harm. Confidence is high because the semantics are unambiguous.
From the tool's definition Tool name 'end_encounter' and description 'End the current combat encounter' indicate a state-modifying action that terminates an active game session state. This is reversible (a new encounter can be started), but alters the game world persistently.
Documented attack patterns abuse exactly the kind of access end_encounter 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 end_encounter:
{
"version": "1",
"default": "deny",
"tools": {
"end_encounter": {
"limits": [
{
"counter": "end_encounter_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}end_encounter stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
End the current combat encounter. It is categorised as a Write tool in the Rpg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rpg MCP server in PolicyLayer and add a rule for end_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 Rpg. Nothing to install.
end_encounter is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the end_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 end_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.
end_encounter 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.