AI agents call get_log_stats 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 queries log statistics using LEQL (Rapid7's log query language) and returns aggregated data without creating, modifying, or deleting any data. The operation is read-only with no side effects. Severity is low because exposure of log statistics poses minimal risk—the worst outcome would be unauthorized visibility into security metrics, not data loss or system compromise.
From the tool's definition Tool name 'get_log_stats' and description 'Get aggregate statistics for a log set over a time range using a LEQL query' indicate retrieval and analysis of log data with no modification.
Attacks that exploit this kind of access
Get aggregate statistics for a log set over a time range using a LEQL query. 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_log_stats: 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_log_stats 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_log_stats 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_log_stats. 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_log_stats 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 →