AI agents call get_sensors to retrieve information from Zont without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns current sensor readings from the ZONT heating system without making any changes to device state or configuration. Misuse poses minimal risk - an agent could at worst spam requests or access temperature/humidity readings, neither of which creates financial loss, system damage, or data destruction. Classified as Read with low severity.
From the tool's definition Tool name 'get_sensors' and description indicate retrieval of sensor data ('Получить список всех датчиков устройства с текущими показаниями' = 'Get list of all device sensors with current readings').
Attacks that exploit this kind of access
Получить список всех датчиков устройства с текущими показаниями:. It is categorised as a Read tool in the Zont MCP Server, which means it retrieves data without modifying state.
Register the Zont MCP server in PolicyLayer and add a rule for get_sensors: 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.
get_sensors is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_sensors 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 get_sensors. 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.
get_sensors 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 →