AI agents call get_execution_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.
This tool retrieves data that has already been executed and computed; it performs no write, execute, destructive, or financial operations. It is purely a data retrieval function with no side effects, fitting the Read category.
From the tool's definition Tool name is 'get_execution_results_csv' and description states 'Retrieve query execution results in CSV format.' The verb 'Retrieve' and the lack of any modification or deletion language indicate this is a read-only operation that fetches previously computed…
Attacks that exploit this kind of access
Retrieve query execution results in CSV format. 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_execution_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_execution_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_execution_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_execution_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_execution_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 →