This record as markdown: /tools/stripe/list-charges.md
What list_charges does on Stripe
AI agents call list_charges to retrieve information from Stripe without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_charges is rated Low
This tool queries and returns a list of charges without creating, modifying, deleting, or executing any operations. It is a straightforward read operation. The low severity reflects that listing charges exposes financial transaction data but does not move money, delete records, or trigger external actions.
From the tool's definition Tool name 'list_charges' and description 'List all charges' indicate a retrieval operation with no mutation or side effects.
Attacks that exploit this kind of access
The rule that runs list_charges safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Stripe, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_charges, this is the rule to start with:
list_charges is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Stripe, apply this rule, and every list_charges call is checked against it from then on.
Questions about list_charges
List all charges. It is categorised as a Read tool in the Stripe MCP Server, which means it retrieves data without modifying state.
Register the Stripe MCP server in PolicyLayer and add a rule for list_charges: 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. Nothing to install.
list_charges 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_charges 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_charges. 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_charges is provided by the Stripe MCP server (@modelcontextprotocol/server-stripe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Stripe, and thousands of servers like it.
This server
Across the catalogue