AI agents call cf_zones to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query operation that retrieves Cloudflare zone metadata. It has no side effects and serves as a lookup mechanism for obtaining zone identifiers needed by other tools. The context of a credential store amplifies the sensitivity of any data exposure, but the tool itself performs only Read operations.
From the tool's definition The description explicitly states 'List all Cloudflare zones' with read-only outputs: 'IDs, status, and name servers'. The tool is informational and retrieves data without creating, modifying, or deleting resources.
Attacks that exploit this kind of access
List all Cloudflare zones (domains) with their IDs, status, and name servers. Use this to get zone IDs needed by cf_dns and cf_create_dns. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for cf_zones: 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 Access. Nothing to install.
cf_zones 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 cf_zones 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_zones. 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_zones is provided by the Access MCP server (scottpedia0/access). 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 →