get_resources
AI agents call get_resources to retrieve information from Kubernetes MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'get_resources' and the server's stated ability to 'get, read, and patch Kubernetes resources' clearly indicates this is a read operation that retrieves data without side effects. While the description is empty, the tool name and sibling context provide strong evidence.
From the tool's definition Tool name contains 'get_resources' and server description indicates this server 'enables interaction with Kubernetes resources' with capability to 'get, read, and patch'. The 'get' operation is explicitly listed as a retrieval function.
Attacks that exploit this kind of access
get_resources. It is categorised as a Read tool in the Kubernetes MCP MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes MCP server in PolicyLayer and add a rule for get_resources: 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. Nothing to install.
get_resources 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_resources 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_resources. 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_resources is provided by the Kubernetes MCP server (yurinnick/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 →