AI agents call get_contexts 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 displays metadata about Kubernetes contexts without modifying, creating, or deleting any resources. It is purely informational and safe for AI agents to invoke.
From the tool's definition Tool name 'get_contexts' and description 'List available kubeconfig contexts and indicate the active one' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List available kubeconfig contexts and indicate the active one. 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_contexts: 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_contexts 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_contexts 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_contexts. 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_contexts 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 →