Get the current kubectl context
AI agents call current-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.
This tool performs a passive information retrieval operation analogous to 'kubectl config current-context'. It does not create, modify, delete, or execute any operations—it simply returns the current context state. The blast radius is minimal, as it exposes only already-available context information. No side effects are possible.
From the tool's definition Tool name 'current-context' and description 'Get the current kubectl context' indicate a read-only query operation that retrieves the active kubectl context configuration without modifying any resources.
Attacks that exploit this kind of access
Get the current kubectl context. 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 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 Kubernetes MCP Server. Nothing to install.
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 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 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.
current-context is provided by the Kubernetes MCP Server MCP server (thekaranpargaie/kube-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 →