Lista refunds de uma cobrança via GET /api/v1/charge/{id}/refund.
AI agents call woovi_get_charge_refunds to retrieve information from Payments MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches refund information for a charge without creating, modifying, deleting, or moving money. Although it operates in a financial context (Woovi/Pagar.me payment gateway), the action itself is purely informational. An AI agent misusing this tool would only gain visibility into refund history, not the ability to execute financial transactions.
From the tool's definition 'Lista refunds de uma cobrança' (Lists refunds of a charge) — the tool retrieves/queries refund data via GET request with no side effects. The GET HTTP method and 'lista' (list) verb confirm read-only retrieval.
Attacks that exploit this kind of access
Lista refunds de uma cobrança via GET /api/v1/charge/{id}/refund. It is categorised as a Read tool in the Payments MCP MCP Server, which means it retrieves data without modifying state.
Register the Payments MCP server in PolicyLayer and add a rule for woovi_get_charge_refunds: 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 Payments MCP. Nothing to install.
woovi_get_charge_refunds 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 woovi_get_charge_refunds 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 woovi_get_charge_refunds. 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.
woovi_get_charge_refunds is provided by the Payments MCP server (lpillonwp/mcp-payments). 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 →