remove_duplicates
AI agents call remove_duplicates to permanently remove resources in DataBeak — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing duplicates typically deletes rows permanently from the dataset, which is an irreversible destructive operation. However, since this server works with CSV data loaded from URLs/strings (potentially in-memory), the blast radius is limited to the current dataset session. Confidence is reduced due to empty description — it's possible this returns a deduplicated copy rather than modifying in place.
From the tool's definition Tool name 'remove_duplicates' implies irreversible deletion of duplicate rows; description is empty providing no additional context.
Attacks that exploit this kind of access
remove_duplicates. It is categorised as a Destructive tool in the DataBeak MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the DataBeak MCP server in PolicyLayer and add a rule for remove_duplicates: 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 DataBeak. Nothing to install.
remove_duplicates is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_duplicates 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 remove_duplicates. 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.
remove_duplicates is provided by the DataBeak MCP server (jonpspri/databeak). 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 →