policy_generation_get
AI agents call policy_generation_get 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.
The 'get' verb indicates a read/retrieval operation with no mutation or execution. However, the empty description reduces confidence. AWS policy generation could theoretically be sensitive data, but retrieval alone is a Read operation. If this tool actually generates or executes policies rather than retrieving them, the category would be Execute, but the name structure ('get') suggests simple retrieval.
From the tool's definition Tool name 'policy_generation_get' suggests retrieval of policy generation artifacts (get operation). Description is empty, limiting specificity.
Attacks that exploit this kind of access
policy_generation_get. 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 policy_generation_get: 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.
policy_generation_get 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 policy_generation_get 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 policy_generation_get. 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.
policy_generation_get 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.