AI agents call get_va_payment to retrieve information from Xendit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves payment details for virtual accounts without creating, modifying, deleting, or executing any operations. It is a passive data query comparable to sibling tools like 'get_balance', 'get_disbursement', and 'get_invoice', which are all read operations. No financial transactions are initiated; existing transaction data is only queried.
From the tool's definition Tool name 'get_va_payment' and description 'Get virtual account payment details' indicate a retrieval operation with no side effects. The verb 'Get' explicitly signals a read-only query.
Attacks that exploit this kind of access
Get virtual account payment details. It is categorised as a Read tool in the Xendit MCP Server, which means it retrieves data without modifying state.
Register the Xendit MCP server in PolicyLayer and add a rule for get_va_payment: 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 Xendit. Nothing to install.
get_va_payment 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 get_va_payment 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 get_va_payment. 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.
get_va_payment is provided by the Xendit MCP server (theyahia/xendit-mcp). 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 →