Charge a previously authorized card
AI agents use charge_authorization to commit financial operations through Paystack — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool executes actual charges against customer payment methods, which constitutes a financial transaction with real monetary consequences. Even though the authorization was obtained previously, executing the charge is an irreversible commitment of funds. Financial transactions are the most severe category per classification rules.
From the tool's definition Tool description states 'Charge a previously authorized card' — a direct financial transaction that moves money. The server context confirms this is a Paystack payment management tool enabling 'manage Paystack payments'.
Documented attack patterns abuse exactly the kind of access charge_authorization 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 charge_authorization:
{
"version": "1",
"default": "deny",
"tools": {
"charge_authorization": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to charge_authorization is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Charge a previously authorized card. It is categorised as a Financial tool in the Paystack MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Paystack MCP server in PolicyLayer and add a rule for charge_authorization: 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.
charge_authorization is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the charge_authorization 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 charge_authorization. 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.
charge_authorization 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.