Explicit re-verify. Returns one row per requested chain: { chain, ok, anchorAddress?, version?, entryCount?, reason?, unsignedEntryCount? }. Useful for periodic integrity checks or after a suspected tamper event. Does NOT throw on per-chain failure — caller inspects the results array. Issue #428:...
AI agents call verify_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 that chain's blob. Otherwise verifies every populated chain. |
Parameters from the server's own tool schema.
Even though verify_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.
Attacks that exploit this kind of access
Explicit re-verify. Returns one row per requested chain: { chain, ok, anchorAddress?, version?, entryCount?, reason?, unsignedEntryCount? }. Useful for periodic integrity checks or after a suspected tamper event. Does NOT throw on per-chain failure — caller inspects the results array. Issue #428: unsignedEntryCount is the count of in-memory unsigned entries on this chain (omitted when zero). When a chain has only unsigned entries, ok: false, reason: "no signed entries on this chain (unsigned-only)", unsignedEntryCount: N so the agent surfaces the unsigned overlay rather than silently dropping it. In demo mode, returns a count of in-memory entries per chain with anchorAddress: "DEMO_ANCHOR". It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
verify_contacts accepts 1 parameter: chain. 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 verify_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.
verify_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 verify_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 verify_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.
verify_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.