AI agents use upload_csv 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.
Uploading CSV data creates new data or appends to existing datasets in Dune Analytics. This is a Write operation (reversible modification) rather than Destructive, as uploads do not irreversibly delete data. Severity is high because an AI agent uploading malicious, corrupted, or sensitive data could compromise analytics integrity and affect downstream users relying on the platform.
From the tool's definition Tool name 'upload_csv' and context within Dune Analytics platform indicating data upload capability. Sibling tools include 'create_table' and 'delete_table', confirming this server manages data persistence. Upload operations create or modify datasets.
Attacks that exploit this kind of access
upload_csv. 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 upload_csv: 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.
upload_csv 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 upload_csv 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 upload_csv. 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.
upload_csv 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 →