AI agents call get_job_results_summary 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 queries and retrieves data from Dune Analytics without side effects. It returns a preview (5 rows) and statistics from previously executed queries. There is no capability to modify, delete, execute code, or commit financial transactions. The limited preview size further constrains potential impact. Classification as Read is appropriate.
From the tool's definition Tool description states 'Get result preview (5 rows) and stats' — a retrieval operation with no modification, deletion, or execution capability. Returns only a limited preview of existing query results.
Attacks that exploit this kind of access
Get result preview (5 rows) and stats. 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_job_results_summary: 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_job_results_summary 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_job_results_summary 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_job_results_summary. 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_job_results_summary 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 →