删除报警规则
AI agents call delete_warning_rule to permanently remove resources in AIRIOT MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting warning/alarm rules is a destructive action that cannot be undone and will permanently remove monitoring configurations. If misused by an AI agent, it could disable critical safety alerts and alarms across the IoT platform, potentially allowing dangerous conditions to go undetected. This fits the Destructive category as it irreversibly removes system configuration data.
From the tool's definition Tool name 'delete_warning_rule' combined with description '删除报警规则' (Chinese: 'delete alarm rule') explicitly performs deletion of alarm rules, an irreversible operation.
Attacks that exploit this kind of access
删除报警规则. It is categorised as a Destructive tool in the AIRIOT MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AIRIOT MCP Server MCP server in PolicyLayer and add a rule for delete_warning_rule: 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 AIRIOT MCP Server. Nothing to install.
delete_warning_rule is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_warning_rule 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 delete_warning_rule. 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.
delete_warning_rule is provided by the AIRIOT MCP Server MCP server (sshwsfc/mcp-server). 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 →