Delete a secret from Vault at the specified path
AI agents call vault_delete to permanently remove resources in Vault MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes secrets from Vault storage. Deletion cannot be undone without backup/recovery procedures outside the tool's control. An AI agent with access could irreversibly destroy critical authentication credentials, encryption keys, or application secrets, causing service outages or security breaches.
From the tool's definition Tool name 'vault_delete' and description 'Delete a secret from Vault at the specified path' explicitly indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete a secret from Vault at the specified path. It is categorised as a Destructive tool in the Vault MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vault MCP Server MCP server in PolicyLayer and add a rule for vault_delete: 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 Vault MCP Server. Nothing to install.
vault_delete 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 vault_delete 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 vault_delete. 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.
vault_delete is provided by the Vault MCP Server MCP server (kelleyblackmore/vault-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 →