Return a customer summary and the customer payment history.
AI agents call get_customer_payments to retrieve information from Stripe Reporting without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries customer payment data. It has no side effects—it does not create, modify, delete, or execute operations. It falls squarely into the Read category. Severity is low because unauthorized disclosure of payment history is a privacy/confidentiality risk but not immediately actionable for financial fraud or account compromise without additional context.
From the tool's definition Tool is part of a 'read-only Stripe finance, ops, and risk reporting' server. The description states it 'Return[s] a customer summary and the customer payment history' with no mutation language.
Attacks that exploit this kind of access
Return a customer summary and the customer payment history. It is categorised as a Read tool in the Stripe Reporting MCP Server, which means it retrieves data without modifying state.
Register the Stripe Reporting MCP server in PolicyLayer and add a rule for get_customer_payments: 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 Stripe Reporting. Nothing to install.
get_customer_payments 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_customer_payments 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_customer_payments. 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_customer_payments is provided by the Stripe Reporting MCP server (ohrytskov/stripe-reporting-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 →