AI agents use update_device_settings to create or update resources in Zont — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zont environment.
The tool modifies device settings in a ZONT heating system. While the description is absent (lowering confidence slightly), the name and server context clearly indicate this performs Write operations that change device configuration. This is categorized as Write rather than Execute because it updates settings/state rather than triggering arbitrary code.
From the tool's definition Tool name 'update_device_settings' indicates modification of device configuration in a heating system (ZONT). Description is empty, but the verb 'update' and context of controlling a heating/boiler system implies reversible state changes.
Attacks that exploit this kind of access
update_device_settings. It is categorised as a Write tool in the Zont MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zont MCP server in PolicyLayer and add a rule for update_device_settings: 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 Zont. Nothing to install.
update_device_settings 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_settings 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_settings. 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_settings is provided by the Zont MCP server (mab2908/zont-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 →