AI agents call storm_get_alerts_inbox to retrieve information from Storm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves alert inbox data for a subscriber without creating, modifying, deleting, or executing any operations. Polling is a read-only operation that simply queries the current state of alerts. The blast radius of misuse is minimal since it only exposes information already available to the authenticated subscriber.
From the tool's definition Tool name includes 'get_alerts' and description states 'Poll the subscriber' — both indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Poll the subscriber. It is categorised as a Read tool in the Storm MCP Server, which means it retrieves data without modifying state.
Register the Storm MCP server in PolicyLayer and add a rule for storm_get_alerts_inbox: 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 Storm. Nothing to install.
storm_get_alerts_inbox 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 storm_get_alerts_inbox 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 storm_get_alerts_inbox. 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.
storm_get_alerts_inbox is provided by the Storm MCP server (xch1tbllc/storm-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 →