Manage workflow executions: get details, list, or delete. Use action=
AI agents call n8n_executions to permanently remove resources in n8n-MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Because the tool spans multiple categories (Read for get/list, Destructive for delete), the most severe applicable category applies. Deleting workflow executions is irreversible — execution history/logs cannot be recovered once purged. This makes it Destructive with high severity given an AI agent could inadvertently purge execution records at scale.
From the tool's definition 'Manage workflow executions: get details, list, or delete' — the tool explicitly supports delete operations on workflow executions
Attacks that exploit this kind of access
Manage workflow executions: get details, list, or delete. Use action=. It is categorised as a Destructive tool in the n8n-MCP 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 n8n_executions: 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-MCP. Nothing to install.
n8n_executions 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 n8n_executions 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 n8n_executions. 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.
n8n_executions is provided by the n8n- MCP server (spring1237/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 →