Retrieve all Kubernetes pods that belong to a specific service. Returns pod names and their current status (Running, Pending, etc.).
AI agents call get_pods_from_service to retrieve information from K8s Observability MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query of Kubernetes cluster metadata (pod membership and status information). It has no capability to modify, delete, execute, or trigger operations. The information returned is observational data used for cluster understanding. Misuse would at worst cause information disclosure or reconnaissance of cluster topology, which is low-risk compared to other categories.
From the tool's definition Tool description explicitly states 'Retrieve all Kubernetes pods' and 'Returns pod names and their current status'. The verb 'Retrieve' and return-only semantics indicate a query operation with no side effects.
Attacks that exploit this kind of access
Retrieve all Kubernetes pods that belong to a specific service. Returns pod names and their current status (Running, Pending, etc.). It is categorised as a Read tool in the K8s Observability MCP MCP Server, which means it retrieves data without modifying state.
Register the K8s Observability MCP server in PolicyLayer and add a rule for get_pods_from_service: 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 K8s Observability MCP. Nothing to install.
get_pods_from_service 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_pods_from_service 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_pods_from_service. 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_pods_from_service is provided by the K8s Observability MCP server (martinimarcello00/k8s-observability-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 →