AI agents call search_public_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 and queries existing public data without creating, modifying, or deleting anything. It has no irreversible effects and does not execute arbitrary code or move funds. The blast radius of misuse is minimal—an AI agent could only discover table names and publicly available queries, which poses no risk of data corruption or financial impact.
From the tool's definition Tool description states 'Search public queries by keyword' and 'discover table names from existing SQL' — these are information retrieval operations with no side effects. The verb 'search' and the purpose of discovery indicate read-only access to metadata.
Attacks that exploit this kind of access
Search public queries by keyword. Use this to discover table names from existing SQL. 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 search_public_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.
search_public_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 search_public_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 search_public_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.
search_public_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 →