Retrieve buffered real-time alerts that arrived since the last poll. Must call subscribe_alerts first.
AI agents call poll_alerts to retrieve information from RedAlert MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves alert data that has already been buffered in the system. It is a read-only operation that fetches information without modifying state, executing code, or triggering external operations. The dependency on subscribe_alerts being called first does not change the fundamental nature of this tool as a data retrieval mechanism.
From the tool's definition Tool name 'poll_alerts' and description 'Retrieve buffered real-time alerts' indicates data retrieval with no side effects. The operation is querying previously received alerts, not modifying, deleting, or executing external actions.
Documented attack patterns abuse exactly the kind of access poll_alerts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RedAlert MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for poll_alerts:
{
"version": "1",
"default": "deny",
"tools": {
"poll_alerts": {}
}
}poll_alerts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve buffered real-time alerts that arrived since the last poll. Must call subscribe_alerts first. It is categorised as a Read tool in the RedAlert MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RedAlert MCP Server MCP server in PolicyLayer and add a rule for poll_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 RedAlert MCP Server. Nothing to install.
poll_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 poll_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 poll_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.
poll_alerts is provided by the RedAlert MCP Server MCP server (ozba/redalert-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RedAlert MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 RedAlert MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.