list_dns_records_tool
AI agents call list_dns_records_tool to retrieve information from MCP Cloudflare without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
DNS record listing is a read-only operation that retrieves existing DNS configuration without side effects. While DNS records are security-sensitive data, exposure of this single read tool poses minimal risk compared to the destructive delete and execute-like create operations available on this server.
From the tool's definition Tool name 'list_dns_records_tool' indicates a listing/querying operation on DNS records with no modification or deletion capability. The sibling tools include separate create/delete/get operations, positioning this as a retrieval function.
Attacks that exploit this kind of access
list_dns_records_tool. It is categorised as a Read tool in the MCP Cloudflare MCP Server, which means it retrieves data without modifying state.
Register the MCP Cloudflare MCP server in PolicyLayer and add a rule for list_dns_records_tool: 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 MCP Cloudflare. Nothing to install.
list_dns_records_tool 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 list_dns_records_tool 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 list_dns_records_tool. 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.
list_dns_records_tool is provided by the MCP Cloudflare MCP server (pypi:mcp-cloudflare-crunchtools). 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 →