save_recipient
Save a payment recipient's bank details for future transfers. The user provides the details once, then you can just say 'pay Maria' in the future.
This record as markdown: /tools/agentpay/save-recipient.md
What save_recipient does on Agentpay
AI agents use save_recipient to create or update resources in Agentpay, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agentpay environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
rut | string | — | Chilean RUT (e.g. '12.345.678-9') |
bank | string | — | Bank name (e.g. 'Banco Estado') |
name | string | Yes | Recipient name (e.g. 'Maria', 'Juan the electrician') |
email | string | — | Recipient email for transfer receipts |
notes | string | — | Notes (e.g. 'cleaning, Tuesdays') |
account_type | string | — | Account type (cuenta corriente, cuenta vista, cuenta rut) |
account_number | string | — | Bank account number |
Parameters from the server's own tool schema.
Why save_recipient is rated Medium
This tool creates and stores sensitive financial information (bank account details) for future use. While it doesn't directly move money (which would be Financial category), it modifies financial records by saving recipient data.
From the tool's definition Tool description states 'Save a payment recipient's bank details for future transfers' — this is a write operation that creates/stores recipient data.
Attacks that exploit this kind of access
The rule that runs save_recipient safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agentpay, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For save_recipient, this is the rule to start with:
save_recipient stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Agentpay, apply this rule, and every save_recipient call is checked against it from then on.
Questions about save_recipient
Save a payment recipient's bank details for future transfers. The user provides the details once, then you can just say 'pay Maria' in the future. It is categorised as a Write tool in the Agentpay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
save_recipient accepts 7 parameters: rut, bank, name, email, notes, account_type, account_number. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Agentpay MCP server in PolicyLayer and add a rule for save_recipient: 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 Agentpay. Nothing to install.
save_recipient is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_recipient 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 save_recipient. 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.
save_recipient is provided by the Agentpay MCP server (agentpay-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agentpay, and thousands of servers like it.
This server
Across the catalogue