AI agents call list_brands 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 tool appears to retrieve or enumerate brands from the urlDNA system without modifying data. Despite the empty description lowering confidence slightly, the naming convention and context of a threat intelligence platform suggest this is a simple read/list operation with minimal blast radius if misused by an agent.
From the tool's definition Tool name 'list_brands' indicates a listing operation with no parameters described; aligns with sibling tools 'list_queries' and 'get_*' patterns which are read-only operations on urlDNA threat intelligence platform.
Documented attack patterns abuse exactly the kind of access list_brands 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_brands:
{
"version": "1",
"default": "deny",
"tools": {
"list_brands": {}
}
}list_brands 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_brands. 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_brands: 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_brands 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_brands 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_brands. 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_brands 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.