sm_storage_health
AI agents call sm_storage_health to retrieve information from Systems Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on naming convention ('_health' suffix) and the sibling tool 'health_check' which is clearly read-only, this tool likely retrieves storage metrics and status without modifying system state. The absence of a description reduces confidence, but the lack of destructive, write, or execute indicators suggests a monitoring/read operation. Classified as Read with medium-low confidence due to missing documentation.
From the tool's definition Tool name 'sm_storage_health' suggests a health-check operation (reading status), with no action verb like 'manage', 'update', 'delete', or 'execute'. Lacks explicit description to confirm function.
Attacks that exploit this kind of access
sm_storage_health. It is categorised as a Read tool in the Systems Manager MCP Server, which means it retrieves data without modifying state.
Register the Systems Manager MCP server in PolicyLayer and add a rule for sm_storage_health: 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 Systems Manager. Nothing to install.
sm_storage_health 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 sm_storage_health 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 sm_storage_health. 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.
sm_storage_health is provided by the Systems Manager MCP server (knuckles-team/systems-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →