cluster_create
AI agents use cluster_create to create or update resources in GreenNode MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GreenNode MCP Server environment.
The name strongly implies creating a new Kubernetes cluster, which is a Write operation (creates new cloud infrastructure). While creating resources is generally reversible (the sibling tool 'cluster_delete' exists), provisioning cloud infrastructure can incur costs and has a high blast radius if misused.
From the tool's definition Tool name 'cluster_create' on a server that manages VNG Cloud infrastructure including Kubernetes resources. Description is empty.
Attacks that exploit this kind of access
cluster_create. It is categorised as a Write tool in the GreenNode MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GreenNode MCP Server MCP server in PolicyLayer and add a rule for cluster_create: 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_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cluster_create 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_create. 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_create 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 →