AI agents use create_query to create or update resources in Dune — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dune environment.
create_query creates and stores new query objects in Dune Analytics, a reversible write operation. While the tool description is empty, the server context (SQL execution platform for blockchain data analysis) and sibling tools (execute_query, archive_query, delete_table) strongly indicate this creates persistent query definitions.
From the tool's definition Tool name 'create_query' paired with sibling tools 'execute_query' and 'execute_sql' in a Dune Analytics MCP context. Server description states 'Execute SQL queries' and 'Manage saved queries', indicating query creation persists data.
Attacks that exploit this kind of access
create_query. It is categorised as a Write tool in the Dune MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dune MCP server in PolicyLayer and add a rule for create_query: 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.
create_query is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_query 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 create_query. 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.
create_query 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 →