AI agents use update_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.
This tool modifies query configuration (SQL and description) reversibly without deleting or executing queries. It's Write rather than Execute because it changes query definitions, not their execution. Severity is medium because query modifications could affect downstream analytics, but changes are reversible and limited to metadata/configuration.
From the tool's definition Tool description states 'Update SQL/description of an existing query', which modifies existing data. The requirement for a Paid Plan indicates access control exists.
Attacks that exploit this kind of access
Update SQL/description of an existing query. (Requires Paid Plan). 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 update_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.
update_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 update_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 update_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.
update_query 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 →