Obtém uma cobrança por id/correlationID via GET /api/v1/charge/{id}.
AI agents call woovi_get_charge 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 retrieves charge information using HTTP GET, which is a safe, non-mutating operation. It does not create, modify, delete, or move money—it only queries existing payment data. Despite operating in a financial context (payment gateway), the tool itself performs no financial transaction or obligation. Severity is low because misuse would only expose existing payment data, not cause financial harm or data loss.
From the tool's definition Tool name 'woovi_get_charge' and description 'Obtém uma cobrança por id/correlationID via GET /api/v1/charge/{id}' (retrieves a charge by id/correlationID via GET request) indicate a read-only query operation.
Attacks that exploit this kind of access
Obtém uma cobrança por id/correlationID via GET /api/v1/charge/{id}. 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: 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 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 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. 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 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 →