AI agents use paystack_create_customer to create or update resources in Paystack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paystack environment.
This tool creates and stores new customer records, which is a reversible write operation. However, the severity is elevated to 'high' rather than 'medium' because it operates within a financial payment system (Paystack), and creating unauthorized or fraudulent customer records could facilitate financial fraud or misuse of the payment infrastructure.
From the tool's definition Tool description states 'Create a new customer on Paystack' — a create operation that modifies data by adding new customer records to the Paystack system.
Attacks that exploit this kind of access
Create a new customer on Paystack. It is categorised as a Write tool in the Paystack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paystack MCP server in PolicyLayer and add a rule for paystack_create_customer: 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_create_customer is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the paystack_create_customer 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_create_customer. 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_create_customer 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 →