AI agents call list_contexts to retrieve information from kube-MCP 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 available Kubernetes contexts, which is a read-only operation that queries cluster configuration. It has no side effects, does not execute code, and does not modify or delete any resources. The blast radius of misuse is minimal—an agent listing contexts gains only informational access to which clusters are configured locally.
From the tool's definition Tool name is 'list_contexts' and description states 'List available Kubernetes contexts' — a query operation that retrieves configuration data without modification.
Attacks that exploit this kind of access
List available Kubernetes contexts. It is categorised as a Read tool in the kube-MCP MCP Server, which means it retrieves data without modifying state.
Register the kube- MCP server in PolicyLayer and add a rule for list_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 kube-MCP. Nothing to install.
list_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 list_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 list_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.
list_contexts is provided by the kube- MCP server (siddjoshi/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 →