Manage location graph for party navigation. Operations: create (new location), get (retrieve location + connections), update (modify properties), delete (remove location), link (connect two locations), unlink (disconnect locations), list (all locations). Supports location types, lighting, hazards...
AI agents use manage_location to create or update resources in ChatRPG — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ChatRPG environment.
While the tool includes a 'delete' operation, the context indicates this manages game world state rather than critical data. Deletion of a location in an RPG is conceptually reversible (can be recreated), distinguishing it from truly destructive operations. The tool enables creation and modification of game locations, which falls primarily under Write.
From the tool's definition Tool description lists operations: 'create (new location)', 'update (modify properties)', 'delete (remove location)', 'link (connect two locations)', 'unlink (disconnect locations)'.
Attacks that exploit this kind of access
Manage location graph for party navigation. Operations: create (new location), get (retrieve location + connections), update (modify properties), delete (remove location), link (connect two locations), unlink (disconnect locations), list (all locations). Supports location types, lighting, hazards, tags, and connection types (door, passage, stairs, ladder, portal, hidden). It is categorised as a Write tool in the ChatRPG MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ChatRPG MCP server in PolicyLayer and add a rule for manage_location: 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.
manage_location 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 manage_location 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 manage_location. 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.
manage_location 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 →