AI agents call get_resource_yaml to retrieve information from K8s without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and outputs existing Kubernetes resource definitions without modifying state. No side effects, reversible operations, code execution, or data destruction occurs. It is a read operation similar to 'kubectl get <resource> -o yaml', which queries cluster state for inspection purposes.
From the tool's definition Tool name 'get_resource_yaml' indicates retrieval of Kubernetes resource definitions in YAML format. The empty description and context of sibling tools (describe_resource, get_configmap, get_contexts) suggest this performs a read-only query operation.
Attacks that exploit this kind of access
get_resource_yaml. It is categorised as a Read tool in the K8s MCP Server, which means it retrieves data without modifying state.
Register the K8s MCP server in PolicyLayer and add a rule for get_resource_yaml: 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. Nothing to install.
get_resource_yaml 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_resource_yaml 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_resource_yaml. 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_resource_yaml is provided by the K8s MCP server (jingyanjiang/k8s-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 →