Delete a credential.
AI agents call n8n_delete_credential to permanently remove resources in Mcp N8n — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a credential removes authentication data that cannot be recovered. This is an irreversible destructive action. While not as severe as Financial (no direct money movement), it ranks high because compromised or missing credentials can break automated workflows and impact downstream systems. The blast radius depends on what that credential is used for, but the action itself is unambiguously destructive.
From the tool's definition Tool name is 'n8n_delete_credential' with description 'Delete a credential.' The verb 'delete' is explicitly destructive and irreversible.
Attacks that exploit this kind of access
Delete a credential. It is categorised as a Destructive tool in the Mcp N8n MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp N8n MCP server in PolicyLayer and add a rule for n8n_delete_credential: 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 Mcp N8n. Nothing to install.
n8n_delete_credential 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_delete_credential 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_delete_credential. 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_delete_credential is provided by the Mcp N8n MCP server (lyzetam/mcp-n8n). 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 →