Create a new CloudFlare zone
AI agents use cf_create_zone to create or update resources in Cargoshipper — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cargoshipper environment.
Creating a new CloudFlare zone is a reversible write operation that modifies infrastructure state by adding a new DNS zone. While it can be undone by deleting the zone, it commits resources and has significant blast radius if misused (e.g., creating zones for domains the agent doesn't own, enabling hijacking scenarios). It is not Destructive because zone creation itself is reversible.
From the tool's definition Tool name 'cf_create_zone' and description 'Create a new CloudFlare zone' indicate this creates a new DNS zone resource in CloudFlare.
Attacks that exploit this kind of access
Create a new CloudFlare zone. It is categorised as a Write tool in the Cargoshipper MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cargoshipper MCP server in PolicyLayer and add a rule for cf_create_zone: 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 Cargoshipper. Nothing to install.
cf_create_zone 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 cf_create_zone 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 cf_create_zone. 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.
cf_create_zone is provided by the Cargoshipper MCP server (scarr7981/cargoshipper-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 →