AI agents call get_query_results_csv 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.
Despite empty description, the name and context (sibling execute_query and get_execution_results tools) strongly indicate this retrieves data without side effects. CSV export is a read operation. Confidence reduced slightly due to missing description, but tool naming convention and server design pattern support Read classification. No write, delete, or execute operations implied.
From the tool's definition Tool name 'get_query_results_csv' indicates retrieval of query results in CSV format. Sibling tools show this server executes queries and returns results; this tool retrieves previously computed results without executing new operations.
Attacks that exploit this kind of access
get_query_results_csv. 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 get_query_results_csv: 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.
get_query_results_csv 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 get_query_results_csv 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 get_query_results_csv. 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.
get_query_results_csv is provided by the Dune MCP server (mwamedacen/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 →