AI agents use update_query to create or update resources in urlDNA MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your urlDNA MCP Server environment.
With no description provided, confidence is reduced, but the tool name clearly indicates a write operation (update = modify reversibly). This is less severe than execute/destructive operations, as it modifies query metadata rather than executing new scans or deleting data.
From the tool's definition Tool name 'update_query' indicates modification of existing data. The server context involves threat intelligence queries on a platform (urlDNA), and 'update_query' modifies stored query configurations or parameters.
Documented attack patterns abuse exactly the kind of access update_query 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 update_query:
{
"version": "1",
"default": "deny",
"tools": {
"update_query": {
"limits": [
{
"counter": "update_query_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_query stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
update_query. It is categorised as a Write tool in the urlDNA MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the urlDNA MCP Server MCP server in PolicyLayer and add a rule for update_query: 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.
update_query is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_query 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 update_query. 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.
update_query 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.