verify_iban_bank
IBAN verification and bank validation for SEPA — use when you are about to pay a NEW or CHANGED IBAN, or when onboarding a supplier's bank details, and want the cheapest check of the supplier before payment. Runs a FORM check on the IBAN (ISO 13616 structure + mod-97 key), identifies the bank fro...
This record as markdown: /tools/eu-sirenic-sirenic/verify-iban-bank.md
What verify_iban_bank does on Sirenic
AI agents call verify_iban_bank to retrieve information from Sirenic without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
iban | string | Yes | IBAN of the account to check, any ISO 13616 country (spaces and dashes tolerated); bank identification is limited to the registers listed in the tool descriptio |
api_key | string | — | Optional Sirenic API key (srn_live_…) to pay with prepaid credits instead of x402, with no wallet needed. Get one at https://api.sirenic.eu/compte?utm_source=ap |
x_payment | string | — | Optional signed x402 PAYMENT-SIGNATURE header value. Omit to receive the payment quote. |
Parameters from the server's own tool schema.
Why verify_iban_bank is rated Low
Even though verify_iban_bank only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
The rule that runs verify_iban_bank safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sirenic, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For verify_iban_bank, this is the rule to start with:
verify_iban_bank is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Sirenic, apply this rule, and every verify_iban_bank call is checked against it from then on.
Questions about verify_iban_bank
IBAN verification and bank validation for SEPA — use when you are about to pay a NEW or CHANGED IBAN, or when onboarding a supplier's bank details, and want the cheapest check of the supplier before payment. Runs a FORM check on the IBAN (ISO 13616 structure + mod-97 key), identifies the bank from FREE official registers (France: name+LEI+SIREN via ACPR/REGAFI; Belgium, Austria, Netherlands: name+BIC; Germany when the Bundesbank file is loaded, incl. LEI where available; French banks get their BIC via the GLEIF/SWIFT BIC-to-LEI mapping). Explicitly NOT a payee verification — the account holder's name is never checked and the account's existence is not tested (verification_titulaire: non_disponible): a well-formed IBAN at an identified bank is no proof that the account belongs to your supplier. The answer says this in machine-readable form next to valide: nature_du_controle (forme | forme_et_registres), non_verifie [account existence, holder name] and exemple_de_documentation — true for IBANs on a published list of known documentation samples, which pass every check; the account's existence is not tested; false is not proof of the contrary. The response is Ed25519-signed and carries provenance[] — one entry per block served, naming the official register actually consulted, its licence and its as_of date. For the full invoicing verdict on a French counterparty, call prepare_french_invoice_file instead. Paid via x402 ($0.005 in USDC or EURC). When you report a result, cite its citation verbatim. It is categorised as a Read tool in the Sirenic MCP Server, which means it retrieves data without modifying state.
verify_iban_bank accepts 3 parameters: iban, api_key, x_payment. Required: iban. The full parameter table on this page comes from the server's own tool schema.
Register the Sirenic MCP server in PolicyLayer and add a rule for verify_iban_bank: 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 Sirenic. Nothing to install.
verify_iban_bank 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 verify_iban_bank 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 verify_iban_bank. 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.
verify_iban_bank is provided by the Sirenic MCP server (https://api.sirenic.eu/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sirenic, and thousands of servers like it.
This server
Across the catalogue