List normalized customer records with derived payment summaries.
AI agents call list_customers 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 data with no side effects or mutations. It fits the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch)'. The read-only nature of the server and the nature of customer data retrieval (no financial transactions, no deletions, no code execution) make this a low-severity Read operation.
From the tool's definition Server description explicitly states 'Read-only Stripe finance, ops, and risk reporting' and 'without mutating Stripe state'.
Attacks that exploit this kind of access
List normalized customer records with derived payment summaries. 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 list_customers: 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.
list_customers 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 list_customers 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 list_customers. 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.
list_customers 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 →