AI agents call get_custom_controls 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 retrieves or lists custom control elements and their associated commands from the ZONT heating system. It is a read-only operation that has no side effects—it does not execute commands, modify settings, delete data, or move money. The low severity reflects minimal risk: knowing what controls exist is informational and poses no direct threat if an AI agent calls it, as no action is taken.
From the tool's definition Tool name 'get_custom_controls' and description 'Получить список пользовательских элементов управления и их команд' (Get list of custom control elements and their commands) indicate a retrieval operation that queries available controls without executing them…
Attacks that exploit this kind of access
Получить список пользовательских элементов управления и их команд. 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_custom_controls: 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_custom_controls 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_custom_controls 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_custom_controls. 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_custom_controls 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 →