cluster_get
AI agents call cluster_get to retrieve information from GreenNode MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' verb indicates a read operation that retrieves cluster information without modifying state. No description is provided, but given the context of similar sibling tools (cluster_get_events, cluster_get_kubeconfig) which are read operations, and the standard REST/API convention where 'get' retrieves data, this tool most likely queries cluster metadata or status.
From the tool's definition Tool name is 'cluster_get' which indicates a retrieval operation. The naming pattern aligns with sibling tools like 'cluster_get_events' and 'cluster_get_kubeconfig' that are clearly read operations.
Attacks that exploit this kind of access
cluster_get. It is categorised as a Read tool in the GreenNode MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GreenNode MCP Server MCP server in PolicyLayer and add a rule for cluster_get: 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 GreenNode MCP Server. Nothing to install.
cluster_get 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 cluster_get 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 cluster_get. 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.
cluster_get is provided by the GreenNode MCP Server MCP server (vngcloud/greennode-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 →