AI agents call diagnose to retrieve information from Idig Dns without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a diagnostic/querying tool that retrieves and reports DNS information. The description indicates it checks resolution status and DNSSEC validity—both read-only operations. It retrieves no data that needs authentication bypass, does not execute shell commands or arbitrary code, does not delete or modify records, and does not commit financial transactions.
From the tool's definition The tool performs 'diagnosis combining resolution + DNSSEC' — pure information gathering without modification or execution of external commands. It queries DNS state and reports findings.
Attacks that exploit this kind of access
Full diagnosis combining resolution + DNSSEC. Use first when something is broken. It is categorised as a Read tool in the Idig Dns MCP Server, which means it retrieves data without modifying state.
Register the Idig Dns MCP server in PolicyLayer and add a rule for diagnose: 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 Idig Dns. Nothing to install.
diagnose 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 diagnose 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 diagnose. 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.
diagnose is provided by the Idig Dns MCP server (https://mcp.softricks.net/sse). 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 →