AI agents call get_dns_zones to retrieve information from LegacyMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix strongly suggests this tool queries and returns DNS zone information without modification. Within the LegacyMCP context of AD assessment, this follows the pattern of other diagnostic tools that expose AD data for querying. Even if misused, reading DNS zones poses minimal direct risk compared to write or destructive operations.
From the tool's definition Tool name 'get_dns_zones' with prefix 'get_' indicates a retrieval operation; no description provided, but naming convention and sibling tools (all prefixed with 'get_') consistently perform read-only queries of Active Directory data.
Attacks that exploit this kind of access
get_dns_zones. It is categorised as a Read tool in the LegacyMCP MCP Server, which means it retrieves data without modifying state.
Register the Legacy MCP server in PolicyLayer and add a rule for get_dns_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 LegacyMCP. Nothing to install.
get_dns_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 get_dns_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 get_dns_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.
get_dns_zones is provided by the Legacy MCP server (marco-lelli/legacy-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 →