Check for current active emergency alerts from subscribed stream
AI agents call check_current_alerts to retrieve information from Pikud Haoref Alert System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves real-time emergency alert information from a subscribed data stream without side effects. It is informational only - checking current status does not create, modify, delete, or execute anything. The blast radius is minimal as misuse would at worst return alert information to an unauthorized party, which while potentially sensitive, does not cause operational harm.
From the tool's definition Tool description states 'Check for current active emergency alerts' - a pure query operation that retrieves alert data with no modification, creation, deletion, or execution of external operations.
Attacks that exploit this kind of access
Check for current active emergency alerts from subscribed stream. It is categorised as a Read tool in the Pikud Haoref Alert System MCP Server, which means it retrieves data without modifying state.
Register the Pikud Haoref Alert System MCP server in PolicyLayer and add a rule for check_current_alerts: 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 Pikud Haoref Alert System. Nothing to install.
check_current_alerts 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 check_current_alerts 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 check_current_alerts. 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.
check_current_alerts is provided by the Pikud Haoref Alert System MCP server (leonmelamud/pikud-a-oref-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 →