AI agents call get_alert to retrieve information from Rapid7 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing alert data from the SIEM with no side effects. It is purely informational. However, severity is elevated from 'low' to 'medium' because alerts in a SIEM often contain sensitive security incident details, system information, and threat intelligence that could be misused if an AI agent has uncontrolled access — for example, leaking confidential incident data or using alert…
From the tool's definition Tool description states 'Get full details of a specific InsightIDR alert' — retrieves alert data without modification. The verb 'Get' and context of querying a SIEM system indicate read-only access to security alert information.
Attacks that exploit this kind of access
Get full details of a specific InsightIDR alert including its detection rule and metadata. It is categorised as a Read tool in the Rapid7 MCP Server, which means it retrieves data without modifying state.
Register the Rapid7 MCP server in PolicyLayer and add a rule for get_alert: 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 Rapid7. Nothing to install.
get_alert 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 get_alert 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 get_alert. 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.
get_alert is provided by the Rapid7 MCP server (solomonneas/rapid7-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 →