Remove a labeled contact. Without chain, removes the label from EVERY chain that has it (one device interaction per chain when removing a signed entry). With chain, removes only that chain's entry — the label can survive on other chains. The unsigned metadata row (notes / tags) is dropped only wh...
AI agents call remove_contact to permanently remove resources in VaultPilot MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
chain | string | — | If specified, removes the label from THAT chain only. If omitted, removes the label from EVERY chain that has it (one device interaction per chain). |
label | string | Yes | Human-readable label, used to look up the contact by name in every prepare flow. Must be unique within a chain — adding the same label twice on the same chain r |
Parameters from the server's own tool schema.
An AI agent that decides to call remove_contact doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from VaultPilot MCP is gone — there is no undo for destructive operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Remove a labeled contact. Without chain, removes the label from EVERY chain that has it (one device interaction per chain when removing a signed entry). With chain, removes only that chain's entry — the label can survive on other chains. The unsigned metadata row (notes / tags) is dropped only when no chain still references the label. Issues CONTACTS_LABEL_NOT_FOUND if neither the signed disk nor the unsigned in-memory store has the label. Issue #428: unsigned-only removals never need a Ledger; mixed labels (signed entry on one chain + unsigned on another) require pairing only for the signed-entry chain. It is categorised as a Destructive tool in the VaultPilot MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
remove_contact accepts 2 parameters: chain, label. Required: label. The full parameter table on this page comes from the server's own tool schema.
Register the VaultPilot MCP server in PolicyLayer and add a rule for remove_contact: 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 VaultPilot MCP. Nothing to install.
remove_contact 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 remove_contact 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 remove_contact. 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.
remove_contact is provided by the VaultPilot MCP server (vaultpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.