Manage theft mechanics, stolen items, and fence NPCs. Actions: steal, check, search, recognize, sell, register_fence, report, decay, get_fence, list_fences Aliases: fence→sell, frisk→search, provenance→check HEAT LEVELS (decay over time): - burning: Just stolen, very high detection - hot: Recent ...
AI agents use theft_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 tool primarily creates and modifies game state (theft records, fence registrations, heat level tracking) rather than executing arbitrary code or permanently destroying data. The 'steal' action records a theft event; 'sell' processes a transaction with game NPCs; 'register_fence' adds NPC data. All are reversible through game mechanics or administrative tools.
From the tool's definition Tool manages theft mechanics including: steal (records thefts), sell (transactions with fence NPCs), register_fence (creates NPC records), and decay (modifies heat levels over time). These are reversible game state modifications.
Documented attack patterns abuse exactly the kind of access theft_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 theft_manage:
{
"version": "1",
"default": "deny",
"tools": {
"theft_manage": {
"limits": [
{
"counter": "theft_manage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}theft_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 theft mechanics, stolen items, and fence NPCs. Actions: steal, check, search, recognize, sell, register_fence, report, decay, get_fence, list_fences Aliases: fence→sell, frisk→search, provenance→check HEAT LEVELS (decay over time): - burning: Just stolen, very high detection - hot: Recent theft, high detection - warm: Moderate detection - cool: Low detection - cold: Safe to sell normally THEFT WORKFLOW: 1. steal - Record a theft 2. check - Check item provenance 3. search - Guard searches character 4. recognize - NPC recognition check 5. report - Report to guards (adds bounty) 6. sell - Sell to fence 7. decay - Process heat over time FENCE WORKFLOW: 1. register_fence - Add fence NPC 2. get_fence - Get fence info 3. list_fences - List all fences. 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 theft_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.
theft_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 theft_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 theft_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.
theft_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.