AI agents call list_queries to retrieve information from urlDNA MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list_' prefix strongly suggests data retrieval with no side effects. Given the security-focused context (threat intelligence platform), listing queries would retrieve metadata about existing threat assessments. This is a non-destructive, non-modifying operation, placing it in the Read category with low severity.
From the tool's definition Tool name 'list_queries' indicates a listing/retrieval operation. Sibling tools like 'get_query', 'get_scan', and 'list_brands' all appear to be read operations.
Documented attack patterns abuse exactly the kind of access list_queries gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and urlDNA MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_queries:
{
"version": "1",
"default": "deny",
"tools": {
"list_queries": {}
}
}list_queries is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_queries. It is categorised as a Read tool in the urlDNA MCP Server MCP Server, which means it retrieves data without modifying state.
Register the urlDNA MCP Server MCP server in PolicyLayer and add a rule for list_queries: 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 urlDNA MCP Server. Nothing to install.
list_queries 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_queries 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_queries. 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_queries is provided by the urlDNA MCP Server MCP server (urldna/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from urlDNA MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 urlDNA MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.