AI agents call get_current_context 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 configuration information about the active Kubernetes context. It performs no write, deletion, code execution, or financial operations. The worst-case misuse would be information disclosure of cluster names and user identities, which is low severity. The operation is purely informational with no side effects.
From the tool's definition Tool name 'get_current_context' and description 'Get the currently active kubeconfig context' indicate a query operation that retrieves cluster and user details without modification.
Attacks that exploit this kind of access
Get the currently active kubeconfig context with cluster and user details. 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_current_context: 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_current_context 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_current_context 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_current_context. 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_current_context 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 →