Update a device.
AI agents use update_device 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.
This tool modifies device properties/settings through the SmartThings API in a way that is typically reversible (settings can be changed again). While it could impact physical device state depending on what is updated, the operation itself is not destructive or irreversible. It falls below Execute severity because it is a targeted modification rather than arbitrary code execution.
From the tool's definition Tool name is 'update_device' and description states 'Update a device.' The verb 'update' indicates modification of existing data in a reversible manner, consistent with Write category operations.
Attacks that exploit this kind of access
Update a device. 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 update_device: 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.
update_device 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 update_device 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 update_device. 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.
update_device 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 →