Cria um customer no Pagar.me (Core API v5).
AI agents use pagarme_create_customer to create or update resources in Payments MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Payments MCP environment.
This tool creates a new customer entity in the Pagar.me payment gateway, which is a reversible data modification (Write category). Severity is high because creating customer records in a payment system can establish financial relationships, enable fraudulent transactions if misused, and affect billing/payment processing.
From the tool's definition Tool name 'pagarme_create_customer' and description 'Cria um customer no Pagar.me (Core API v5)' indicate creation of a customer record in a payment gateway system.
Attacks that exploit this kind of access
Cria um customer no Pagar.me (Core API v5). It is categorised as a Write tool in the Payments MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Payments MCP server in PolicyLayer and add a rule for pagarme_create_customer: 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.
pagarme_create_customer 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 pagarme_create_customer 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 pagarme_create_customer. 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.
pagarme_create_customer 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 →