Audit a single FX transaction against the mid-market rate. Returns score (1-10), spread %, hidden fee, and rating. Free for first 3 calls per month per IP — after that returns 402 Payment Required.
AI agents call audit_transaction to retrieve information from iPayX FX Audit — Hidden Bank Fee Detector without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
amount | number | — | Transaction amount in currency_from |
bank_rate | number | — | The rate the bank/broker actually charged |
currency_to | string | — | |
currency_from | string | — |
Parameters from the server's own tool schema.
The tool performs a read/query operation: it takes transaction data as input, compares it against mid-market rates, and returns analytical results (score, spread %, hidden fee, rating). There is no indication it moves money, modifies records, executes code, or deletes anything. The 402 Payment Required gate is a billing mechanism, not a risk factor for the tool's action.
From the tool's definition 'Audit a single FX transaction against the mid-market rate. Returns score (1-10), spread %, hidden fee, and rating.' — the tool retrieves and computes analytical metrics about a transaction; no data is created, modified, or deleted.
Documented attack patterns abuse exactly the kind of access audit_transaction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and iPayX FX Audit — Hidden Bank Fee Detector, and nothing reaches the server without passing your rules. This is the rule we recommend for audit_transaction:
{
"version": "1",
"default": "deny",
"tools": {
"audit_transaction": {}
}
}audit_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.
Audit a single FX transaction against the mid-market rate. Returns score (1-10), spread %, hidden fee, and rating. Free for first 3 calls per month per IP — after that returns 402 Payment Required. It is categorised as a Read tool in the iPayX FX Audit — Hidden Bank Fee Detector MCP Server, which means it retrieves data without modifying state.
audit_transaction accepts 4 parameters: amount, bank_rate, currency_to, currency_from. The full parameter table on this page comes from the server's own tool schema.
Register the iPayX FX Audit — Hidden Bank Fee Detector MCP server in PolicyLayer and add a rule for audit_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 iPayX FX Audit — Hidden Bank Fee Detector. Nothing to install.
audit_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 audit_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 audit_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.
audit_transaction is provided by the iPayX FX Audit — Hidden Bank Fee Detector MCP server (ybolduc/ipayx-fx-audit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from iPayX FX Audit — Hidden Bank Fee Detector, 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.
3 iPayX FX Audit — Hidden Bank Fee Detector tools catalogued and risk-classified — across an index of 43,000+ MCP servers.