Inspect Kubernetes network policies: list and describe.
AI agents call k8s_network_policies to retrieve information from RedisNexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only inspects and retrieves information about Kubernetes network policies through list and describe operations. It has no side effects, does not modify infrastructure, and cannot execute commands or trigger deployments. The blast radius of misuse is limited to information disclosure about network configuration, making it a Read category tool with low severity.
From the tool's definition The tool description states it can 'list and describe' Kubernetes network policies, which are read-only retrieval operations with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Inspect Kubernetes network policies: list and describe. It is categorised as a Read tool in the RedisNexus MCP Server, which means it retrieves data without modifying state.
Register the RedisNexus MCP server in PolicyLayer and add a rule for k8s_network_policies: 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 RedisNexus. Nothing to install.
k8s_network_policies 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 k8s_network_policies 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 k8s_network_policies. 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.
k8s_network_policies is provided by the RedisNexus MCP server (rajkumar-madhu/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 →