管理Kubernetes上下文
AI agents call kubectl_context to retrieve information from Kubernetes MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Kubernetes context operations are informational in nature. They retrieve current context, list available contexts, or switch between existing contexts in kubeconfig. These are read operations that do not create, modify, delete, or execute actions on cluster resources.
From the tool's definition Tool name 'kubectl_context' with description '管理Kubernetes上下文' (manage Kubernetes context). Context management involves querying, switching, and listing Kubernetes cluster contexts—operations that retrieve or query configuration state without modifying…
Attacks that exploit this kind of access
管理Kubernetes上下文. It is categorised as a Read tool in the Kubernetes MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes MCP Server MCP server in PolicyLayer and add a rule for kubectl_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 Kubernetes MCP Server. Nothing to install.
kubectl_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 kubectl_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 kubectl_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.
kubectl_context is provided by the Kubernetes MCP Server MCP server (secret-deus/kubernetes-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 →