⚠️ DESTRUCTIVE: Delete a dataset item permanently from the dataset.
AI agents call delete_dataset_item to permanently remove resources in Langfuse MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes data without the ability to undo the operation. Permanent deletion is irreversible and cannot be recovered, making it the most severe category (Destructive ranks above Execute and Write). If an AI agent misuses this tool, it could remove critical dataset items that cannot be restored, causing data loss.
From the tool's definition Tool name is 'delete_dataset_item' with description explicitly stating '⚠️ DESTRUCTIVE: Delete a dataset item permanently from the dataset.' The word 'Delete' combined with 'permanently' and the explicit ⚠️ DESTRUCTIVE warning confirms irreversible data…
Attacks that exploit this kind of access
⚠️ DESTRUCTIVE: Delete a dataset item permanently from the dataset. It is categorised as a Destructive tool in the Langfuse MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Langfuse MCP Server MCP server in PolicyLayer and add a rule for delete_dataset_item: 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 Langfuse MCP Server. Nothing to install.
delete_dataset_item 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 delete_dataset_item 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 delete_dataset_item. 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.
delete_dataset_item is provided by the Langfuse MCP Server MCP server (therealsachin/langfuse-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 →