Delete a dataset version. Destructive: confirm='yes' required.
AI agents call roboflow_delete_version to permanently remove resources in Roboflow MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes an entire dataset version, which cannot be undone. The explicit 'Destructive' label in the description and the requirement for a confirmation parameter further confirm this is a destructive operation. High severity due to potential loss of significant ML training data and project history.
From the tool's definition Tool name contains 'delete'; description explicitly states 'Delete a dataset version' and 'Destructive: confirm=yes required'
Attacks that exploit this kind of access
Delete a dataset version. Destructive: confirm='yes' required. It is categorised as a Destructive tool in the Roboflow MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Roboflow MCP Server MCP server in PolicyLayer and add a rule for roboflow_delete_version: 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 Roboflow MCP Server. Nothing to install.
roboflow_delete_version 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 roboflow_delete_version 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 roboflow_delete_version. 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.
roboflow_delete_version is provided by the Roboflow MCP Server MCP server (mayankd409/roboflow-mcp-server). 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 →