AI agents use agent_manage 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 word 'manage' typically implies create/update/delete operations on NPC entities. Given the RPG context and sibling tools (character_manage, aura_manage, concentration_manage all follow the same 'manage' pattern suggesting CRUD), this is most likely a Write operation for creating or modifying NPC agent records. The description is cut off so confidence is reduced.
From the tool's definition Manage LLM-driven NPCs — description is truncated and uninformative beyond 'manage' NPCs
Documented attack patterns abuse exactly the kind of access agent_manage 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 agent_manage:
{
"version": "1",
"default": "deny",
"tools": {
"agent_manage": {
"limits": [
{
"counter": "agent_manage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}agent_manage 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.
Manage LLM-driven NPCs (. 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 agent_manage: 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.
agent_manage 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 agent_manage 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 agent_manage. 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.
agent_manage 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.