find_pod_restarts
AI agents call find_pod_restarts to retrieve information from Loki MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Kubernetes cluster logs via Grafana Loki to detect pod restart patterns—a read operation with no side effects. However, the ability to monitor pod restarts could enable reconnaissance of cluster instability or targeted disruption detection, warranting medium severity.
From the tool's definition Tool name 'find_pod_restarts' and sibling tools ('get_error_summary', 'get_pod_logs', 'list_namespaces', 'search_logs') indicate read-only log analysis operations. Server description emphasizes 'query and analyze' operations including 'pod restart detection'.
Attacks that exploit this kind of access
find_pod_restarts. It is categorised as a Read tool in the Loki MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Loki MCP Server MCP server in PolicyLayer and add a rule for find_pod_restarts: 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 Loki MCP Server. Nothing to install.
find_pod_restarts 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 find_pod_restarts 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 find_pod_restarts. 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.
find_pod_restarts is provided by the Loki MCP Server MCP server (mvs5465-test/loki-mcp-server). 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 →