AI agents call cf_dns 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 tool queries and retrieves DNS record information from Cloudflare without modifying, creating, or deleting any records. It is a read-only operation. However, severity is elevated to medium because DNS configuration details can be sensitive: the output reveals infrastructure topology, service locations, and security posture (e.g., which services are proxied vs. exposed).
From the tool's definition Tool name 'cf_dns' and description states 'List all DNS records' with purpose to 'audit DNS configuration or check for existing records' — a retrieval operation with no data modification.
Attacks that exploit this kind of access
List all DNS records for a Cloudflare zone including type, name, content, TTL, and proxy status. Use this to audit DNS configuration or check for existing records before creating new ones. 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_dns: 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_dns 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_dns 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_dns. 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_dns 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 →