Delete a field from a vector layer.
AI agents call delete_field to permanently remove resources in QGIS MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a field from a vector layer is irreversible data destruction. Once removed, the field and all its associated data across all features are permanently lost unless a backup or undo history exists. This action cannot be undone through normal reversal (unlike a Write operation that could be updated).
From the tool's definition Tool name explicitly states 'delete_field' and description confirms it 'Delete a field from a vector layer.' The verb 'delete' combined with the irreversible nature of removing a field from a GIS dataset indicates destructive action.
Attacks that exploit this kind of access
Delete a field from a vector layer. It is categorised as a Destructive tool in the QGIS MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the QGIS MCP server in PolicyLayer and add a rule for delete_field: 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 QGIS MCP. Nothing to install.
delete_field 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_field 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_field. 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_field is provided by the QGIS MCP server (nkarasiak/qgis-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 →