AI agents call get_execution_results 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 the empty description, the naming convention and context of sibling tools (execute_query, execute_sql, get_execution_status, get_execution_results_csv) clearly indicate this is a Read operation that retrieves cached or stored results from an already-executed query. It has no side effects—it queries data without modification, creation, or deletion.
From the tool's definition Tool name 'get_execution_results' indicates retrieval of previously computed query results; sibling tools like 'execute_query' and 'execute_sql' perform the actual computation, while this tool fetches their output.
Attacks that exploit this kind of access
get_execution_results. 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: 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 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 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. 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 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 →