Get details of a transaction by ID
AI agents call fetch_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 retrieves transaction details without creating, modifying, or deleting data. It is a Read operation. However, severity is elevated to 'medium' rather than 'low' because the fetched transaction data may be sensitive financial information (customer details, payment amounts, timestamps, etc.) that an agent could exfiltrate or misuse, even though the tool itself performs no destructive action.
From the tool's definition Tool name is 'fetch_transaction' and description states 'Get details of a transaction by ID' — a retrieval operation with no modifications or side effects.
Documented attack patterns abuse exactly the kind of access fetch_transaction 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 fetch_transaction:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_transaction": {}
}
}fetch_transaction is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get details of a transaction by ID. 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 fetch_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.
fetch_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 fetch_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 fetch_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.
fetch_transaction 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.