Delete a workflow. Requires write_mode.
AI agents call delete_workflow to permanently remove resources in N8n — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a workflow irreversibly removes automation logic and associated configurations. This cannot be undone and represents permanent data loss. The operation affects all dependent processes and cannot be recovered. This is the most severe category (Destructive > Execute > Write > Read).
From the tool's definition 'Delete a workflow' - the tool permanently removes a workflow, which is irreversible data destruction. The requirement for 'write_mode' indicates the system recognizes this as a sensitive destructive operation.
Attacks that exploit this kind of access
Delete a workflow. Requires write_mode. It is categorised as a Destructive tool in the N8n MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the N8n MCP server in PolicyLayer and add a rule for delete_workflow: 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 N8n. Nothing to install.
delete_workflow 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_workflow 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_workflow. 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_workflow is provided by the N8n MCP server (siddharth0903/n8n-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 →