Perform a vault action: vault_init, vault_store, vault_retrieve, vault_list, vault_delete, vault_rotate, vault_audit.
AI agents call vault_action to permanently remove resources in UnClick — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
key | string | — | |
value | string | — | |
action | string | Yes | |
encrypt | boolean | — | |
master_password | string | Yes |
Parameters from the server's own tool schema.
This tool bundles multiple vault operations including vault_delete (irreversible removal of secrets) and vault_rotate (overwrites/rotates credentials, which can break dependent services). Per the severity escalation rules, the most severe applicable category is Destructive.
From the tool's definition vault_delete, vault_rotate, vault_audit — includes irreversible deletion and rotation of vault secrets/credentials
Attacks that exploit this kind of access
Perform a vault action: vault_init, vault_store, vault_retrieve, vault_list, vault_delete, vault_rotate, vault_audit. It is categorised as a Destructive tool in the UnClick MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
vault_action accepts 5 parameters: key, value, action, encrypt, master_password. Required: action, master_password. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for vault_action: 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 UnClick. Nothing to install.
vault_action 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_action 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_action. 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_action is provided by the UnClick MCP server (@unclick/mcp-server). 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 →