AI agents use create_table 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.
The tool creates new tables, which is a reversible Write operation. While it modifies the Dune Analytics state, it is not irreversible (tables can be deleted via delete_table) and does not execute arbitrary code or move funds. High severity due to potential for unauthorized data persistence and blast radius across analytical queries depending on that table.
From the tool's definition Tool name 'create_table' and server context showing 'upload custom datasets' and 'Manage saved queries' indicate data creation/modification capabilities. The server enables writing to Dune Analytics platform.
Attacks that exploit this kind of access
create_table. 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_table: 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_table 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_table 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_table. 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_table 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 →