AI agents call paystack_verify_transaction 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 queries transaction status information without creating, modifying, deleting, or moving money. It is a read-only operation. While the server overall handles financial operations, this specific tool only reads/verifies existing transaction data. Severity is low because verification has no side effects and cannot cause financial harm through misuse.
From the tool's definition Tool name 'paystack_verify_transaction' and description 'Verify the status of a transaction by its reference' indicate a lookup/query operation that retrieves transaction status without modifying data.
Attacks that exploit this kind of access
Verify the status of a transaction by its reference. 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_verify_transaction: 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_verify_transaction 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_verify_transaction 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_verify_transaction. 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_verify_transaction 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 →