Whitelist or blacklist a customer
AI agents use set_customer_risk_action 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 modifies a customer's risk status (whitelist or blacklist), which is a reversible write operation. However, it carries high severity because blacklisting a customer could block them from making payments, causing significant business impact if misused by an AI agent.
From the tool's definition Whitelist or blacklist a customer
Documented attack patterns abuse exactly the kind of access set_customer_risk_action gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Paystack, and nothing reaches the server without passing your rules. This is the rule we recommend for set_customer_risk_action:
{
"version": "1",
"default": "deny",
"tools": {
"set_customer_risk_action": {
"limits": [
{
"counter": "set_customer_risk_action_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} set_customer_risk_action stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Whitelist or blacklist a customer. 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 set_customer_risk_action: 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.
set_customer_risk_action 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 set_customer_risk_action 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 set_customer_risk_action. 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.
set_customer_risk_action is provided by the Paystack MCP server (kohasummons/paystack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Paystack, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
28 Paystack tools catalogued and risk-classified — across an index of 43,000+ MCP servers.