AI agents call list_user_queries to retrieve information from Dune without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data (listing existing queries) without side effects. It is a straightforward read operation that fits the 'Read' category. Severity is low because listing queries poses minimal risk — it exposes metadata about queries but not sensitive data execution or financial impact. Confidence is high because the name and description unambiguously describe a list/retrieval action.
From the tool's definition Tool name is 'list_user_queries' and description states 'List queries by user handle' — a retrieval operation with no modification or execution.
Attacks that exploit this kind of access
List queries by user handle. It is categorised as a Read tool in the Dune MCP Server, which means it retrieves data without modifying state.
Register the Dune MCP server in PolicyLayer and add a rule for list_user_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 Dune. Nothing to install.
list_user_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_user_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_user_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_user_queries is provided by the Dune MCP server (nice-bills/dune-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 →