verify_french_invoice
Invoice verification for France — use when you HOLD an invoice (or its extracted fields) and must check that the identifiers it displays belong together before paying it. Cross-checks in ONE call: the SIREN against the official registry (existence and active status, live), the VAT number printed ...
This record as markdown: /tools/eu-sirenic-sirenic/verify-french-invoice.md
What verify_french_invoice does on Sirenic
AI agents call verify_french_invoice 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 |
|---|---|---|---|
tva | string | — | VAT number printed on the invoice, e.g. FR27552032534 — cross-checked against the SIREN and live against VIES. At least one of tva/iban is required |
iban | string | — | IBAN printed on the invoice (spaces tolerated) — form + key + bank identification, never a holder-name check. At least one of tva/iban is required |
siren | string | Yes | 9-digit SIREN printed on the invoice (digits only) |
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_french_invoice is rated Low
Even though verify_french_invoice 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) · Admin/system-level operation
Attacks that exploit this kind of access
The rule that runs verify_french_invoice 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_french_invoice, this is the rule to start with:
verify_french_invoice 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_french_invoice call is checked against it from then on.
Questions about verify_french_invoice
Invoice verification for France — use when you HOLD an invoice (or its extracted fields) and must check that the identifiers it displays belong together before paying it. Cross-checks in ONE call: the SIREN against the official registry (existence and active status, live), the VAT number printed on the invoice against the one computed from the SIREN (the French key is deterministic) AND live against VIES, and the IBAN's ISO 13616 form + key digits with the bank identified. Returns a deterministic verdict coherent/incoherent/inverifiable with closed-list reasons traced to their source — flags a VAT number that belongs to ANOTHER company, a ceased supplier, or a key-invalid IBAN. A VIES outage yields inverifiable, never a false invalid. NOT a payee verification: the bank leg checks form only — a valid-but-swapped IBAN is not detectable, and non_verifie says so next to the verdict. At least one of tva/iban is required (a SIREN alone is a profile, not a cross-check). An incomplete identity (administrative status or legal category missing from the Sirene register) yields inverifiable, reason identite_incomplete, unless an inconsistency is found. Paid via x402 ($0.02 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_french_invoice accepts 5 parameters: tva, iban, siren, api_key, x_payment. Required: siren. 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_french_invoice: 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_french_invoice 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_french_invoice 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_french_invoice. 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_french_invoice 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