更新报警规则
AI agents use update_warning_rule to create or update resources in AIRIOT MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AIRIOT MCP Server environment.
Updating warning rules qualifies as Write because it modifies existing data (alarm rule configurations) reversibly—changes can be undone or corrected. It is not Execute because it does not run arbitrary code or trigger external operations; it updates configuration. It is not Destructive because the changes are reversible and do not permanently delete data.
From the tool's definition Tool name is 'update_warning_rule'; description translates to 'update alarm rule'. The tool modifies warning/alarm rules in an IoT platform, which are reversible configuration changes.
Attacks that exploit this kind of access
更新报警规则. It is categorised as a Write tool in the AIRIOT MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AIRIOT MCP Server MCP server in PolicyLayer and add a rule for update_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.
update_warning_rule 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_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 update_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.
update_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 →