AI agents use create_dns_record to create or update resources in Vultr Dns — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vultr Dns environment.
Creating DNS records modifies domain configuration and can redirect traffic, change service endpoints, or enable malicious domain hijacking if misused by an AI agent without proper authorization constraints. This is a Write operation (creates data reversibly) with high severity due to the potential to disrupt services or facilitate attacks, though not as critical as Destructive operations that cannot be undone.
From the tool's definition Tool name 'create_dns_record' and description 'Create a new DNS record for a domain' indicate creation of DNS records, which are data structures that modify domain resolution behavior.
Attacks that exploit this kind of access
Create a new DNS record for a domain. It is categorised as a Write tool in the Vultr Dns MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vultr Dns MCP server in PolicyLayer and add a rule for create_dns_record: 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 Vultr Dns. Nothing to install.
create_dns_record 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 create_dns_record 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 create_dns_record. 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.
create_dns_record is provided by the Vultr Dns MCP server (rsp2k/vultr-dns-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 →