describe_log_groups
AI agents call describe_log_groups 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 'describe_' prefix in AWS APIs consistently denotes read-only operations that retrieve information about resources. No side effects or modifications occur. Even though the description is empty, the naming convention strongly indicates this is a data retrieval operation. Severity is low as log group metadata is typically non-sensitive and reading logs does not affect infrastructure.
From the tool's definition Tool name 'describe_log_groups' indicates querying/retrieving metadata about log groups; 'describe' pattern is a standard AWS operation for fetching information without modification.
Attacks that exploit this kind of access
describe_log_groups. 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 describe_log_groups: 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.
describe_log_groups 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 describe_log_groups 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 describe_log_groups. 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.
describe_log_groups 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.