Return the joined per-label view across chains. Each row contains the label, addresses keyed by chain, optional notes / tags, the earliest addedAt across the joined entries, and an optional unsigned: true flag (issue #428) when at least one chain entry is unsigned (in-memory only). Strict-fail on...
AI agents call list_contacts to retrieve information from VaultPilot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
chain | string | — | If specified, only verifies + returns entries for that chain. Otherwise returns the joined per-label view across all chains with at least one verified entry. |
label | string | — | Filter to a specific label. Useful for 'show me what we know about Mom' single-record reads. |
Parameters from the server's own tool schema.
Even though list_contacts only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Return the joined per-label view across chains. Each row contains the label, addresses keyed by chain, optional notes / tags, the earliest addedAt across the joined entries, and an optional unsigned: true flag (issue #428) when at least one chain entry is unsigned (in-memory only). Strict-fail on tamper (signed disk blobs): any signature failure / anchor mismatch / version rollback throws immediately (CONTACTS_TAMPERED / CONTACTS_ANCHOR_MISMATCH / CONTACTS_VERSION_ROLLBACK) rather than silently dropping rows — agents must surface the failure to the user. Unsigned in-memory entries are merged on top of the verified signed view; signed entries always win on a per-(label, chain) basis. In demo mode, the demo in-memory store is read directly (no signature path); all four chains supported, every row is unsigned: true. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
list_contacts accepts 2 parameters: chain, 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 list_contacts: 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.
list_contacts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_contacts 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 list_contacts. 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.
list_contacts 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.