get_logs_insight_query_results
AI agents call get_logs_insight_query_results to retrieve information from Amazon MQ MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves query results from logs (Read operation). Severity is medium because logs may contain sensitive information (credentials, PII, internal system details) that could be exfiltrated if an agent misuses this tool, though the operation itself is non-destructive and non-financial.
From the tool's definition Tool name 'get_logs_insight_query_results' indicates retrieval of log query results; no modification verbs present. Description is empty, limiting confidence. Sibling tools include 'analyze_log_group' suggesting log/monitoring operations.
Attacks that exploit this kind of access
get_logs_insight_query_results. It is categorised as a Read tool in the Amazon MQ MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon MQ MCP Server MCP server in PolicyLayer and add a rule for get_logs_insight_query_results: 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 Amazon MQ MCP Server. Nothing to install.
get_logs_insight_query_results 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_logs_insight_query_results 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_logs_insight_query_results. 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_logs_insight_query_results is provided by the Amazon MQ MCP Server MCP server (awslabs.amazon-mq-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.