get_promql_labels
AI agents call get_promql_labels 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 naming convention 'get_' combined with 'promql_labels' suggests this tool retrieves or enumerates labels from a Prometheus-compatible metrics system. This is a read-only operation with no data modification capability. Severity is medium (not low) because querying metrics infrastructure could expose sensitive operational or system configuration details that might inform an attacker's reconnaissance.
From the tool's definition Tool name 'get_promql_labels' indicates retrieval of PromQL (Prometheus Query Language) labels, which is a query operation. Description is empty, limiting confidence.
Attacks that exploit this kind of access
get_promql_labels. 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_promql_labels: 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_promql_labels 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_promql_labels 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_promql_labels. 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_promql_labels 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.