get_resource
AI agents call get_resource to retrieve information from Amazon SageMaker AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'get_resource' strongly implies a retrieval operation with no modification or deletion. In AWS SageMaker and general cloud APIs, 'get' operations are standard read-only accessors. Without a description, confidence is moderate, but the naming convention and absence of action verbs like 'create', 'delete', or 'execute' support classification as Read. Blast radius is limited to information disclosure.
From the tool's definition Tool name 'get_resource' combined with typical AWS resource retrieval patterns and placement among sibling tools (aggregate, analyze_*) suggests a data retrieval operation. Description is empty, limiting confidence.
Attacks that exploit this kind of access
get_resource. It is categorised as a Read tool in the Amazon SageMaker AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon SageMaker AI MCP Server MCP server in PolicyLayer and add a rule for get_resource: 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 SageMaker AI MCP Server. Nothing to install.
get_resource 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_resource 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_resource. 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_resource is provided by the Amazon SageMaker AI MCP Server MCP server (awslabs.sagemaker-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.