AI agents call paystack_list_banks to retrieve information from Paystack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static reference data (supported banks) for a country. It has no capability to modify data, execute transactions, or produce side effects. While it exists on a financial platform (Paystack), the tool itself does not move money, create charges, or alter system state. The maximum potential harm is limited to information disclosure of publicly-available bank listings, hence low severity.
From the tool's definition Tool name 'paystack_list_banks' and description 'List banks supported by Paystack for a given country' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List banks supported by Paystack for a given country. It is categorised as a Read tool in the Paystack MCP Server, which means it retrieves data without modifying state.
Register the Paystack MCP server in PolicyLayer and add a rule for paystack_list_banks: 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 Paystack. Nothing to install.
paystack_list_banks 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 paystack_list_banks 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 paystack_list_banks. 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.
paystack_list_banks is provided by the Paystack MCP server (trinity-21/mcp-server-paystack). 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 →