Create a room in a location.
AI agents use create_room to create or update resources in SmartThingsMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SmartThingsMCP environment.
The tool creates (writes) a new room resource within a SmartThings location. Creation is reversible and has no side effects beyond the new room object being added to the system. It does not execute commands, delete data irreversibly, move money, or trigger external operations. Severity is low because creating a room has minimal blast radius—worst case is minor organizational clutter in the device hierarchy.
From the tool's definition Tool name 'create_room' and description 'Create a room in a location' indicate data creation operation. This is reversible as rooms can be deleted via the sibling tool 'delete_room'.
Attacks that exploit this kind of access
Create a room in a location. It is categorised as a Write tool in the SmartThingsMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SmartThings MCP server in PolicyLayer and add a rule for create_room: 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 SmartThingsMCP. Nothing to install.
create_room 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 create_room 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 create_room. 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.
create_room is provided by the SmartThings MCP server (technohead/smartthings-mcp). 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 →