Return the normalized details for a single payment, including refunds and disputes.
AI agents call get_payment 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 financial transaction data from Stripe without side effects. It is a read-only query operation that fits the 'Read' category (retrieves or queries data; no side effects). The severity is low because unauthorized access to payment details, while sensitive, does not enable direct financial harm compared to tools that could execute transfers or delete records.
From the tool's definition Tool name 'get_payment' and description 'Return the normalized details for a single payment' clearly indicates a retrieval operation. Server description emphasizes 'Read-only' access that 'Enables querying' without 'mutating Stripe state'.
Attacks that exploit this kind of access
Return the normalized details for a single payment, including refunds and disputes. 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_payment: 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_payment 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_payment 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_payment. 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_payment 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 →