Get enhanced recommendation details with integrated data from multiple AWS services.
AI agents call rec-details to retrieve information from AWS IoT SiteWise 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 and queries existing recommendation data by integrating information from multiple sources. The verb 'Get' indicates a read-only operation that does not create, modify, delete, or execute any actions. No data is altered or side effects are triggered by calling this tool.
From the tool's definition The tool description states it 'Get[s] enhanced recommendation details' - a retrieval operation with 'no side effects'. It integrates data from multiple AWS services but performs only a query/fetch operation.
Attacks that exploit this kind of access
Get enhanced recommendation details with integrated data from multiple AWS services. It is categorised as a Read tool in the AWS IoT SiteWise MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS IoT SiteWise MCP Server MCP server in PolicyLayer and add a rule for rec-details: 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 AWS IoT SiteWise MCP Server. Nothing to install.
rec-details 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 rec-details 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 rec-details. 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.
rec-details is provided by the AWS IoT SiteWise MCP Server MCP server (awslabs.aws-iot-sitewise-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.