AI agents call get_server_health to retrieve information from Cimc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves composite health information from the server without creating, modifying, deleting, or executing operations. It is purely informational monitoring, similar to sibling tools like 'get_sensors', 'get_event_log', and 'get_power_stats'. No side effects or state changes occur.
From the tool's definition Tool name 'get_server_health' and description indicate retrieval of status information ('server status, active faults, DIMM/PSU/fan/storage status, and power consumption'). The verb 'get' and lack of any modification language confirm read-only data retrieval.
Attacks that exploit this kind of access
Composite health check: server status, active faults, DIMM/PSU/fan/storage status, and power consumption. Answers. It is categorised as a Read tool in the Cimc MCP Server, which means it retrieves data without modifying state.
Register the Cimc MCP server in PolicyLayer and add a rule for get_server_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 Cimc. Nothing to install.
get_server_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 get_server_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 get_server_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.
get_server_health is provided by the Cimc MCP server (schwarztim/cimc-mcp). 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 →