AI agents call get_faults 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 retrieves and lists fault data from the server's monitoring system. It performs no side effects, creates no new data, executes no commands, and deletes nothing. The optional filtering is a read-only parameter. Misuse by an AI agent would only result in information disclosure of operational status, which has minimal blast radius.
From the tool's definition Tool name 'get_faults' with description 'List all active faults with severity, description, cause, and timestamps.
Attacks that exploit this kind of access
List all active faults with severity, description, cause, and timestamps. Optionally filter by severity level. 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_faults: 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_faults 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_faults 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_faults. 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_faults 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 →