AI agents call get_boiler_errors 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 queries the state of the heating system to retrieve error and fault information. It performs a read-only operation that retrieves diagnostic data about the boiler's current errors and alarm states. No side effects, modifications, deletions, or external actions are triggered.
From the tool's definition Tool name 'get_boiler_errors' and description 'Получить текущие ошибки и аварийные состояния котла' (Get current errors and emergency states of the boiler) indicate a retrieval operation with no data modification.
Attacks that exploit this kind of access
Получить текущие ошибки и аварийные состояния котла. 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_boiler_errors: 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_boiler_errors 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_boiler_errors 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_boiler_errors. 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_boiler_errors 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 →