Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Prepare French invoice file

prepare_french_invoice_file
Read-only

Verify a French company before invoicing or paying it: returns legal identity, VIES-checked VAT, IBAN structure and bank identification, plus a signed readiness verdict.

Instructions

Use when you are about to invoice or pay a FRENCH company and must verify the supplier before payment: onboarding, first invoice, first payment, or bank details that just changed. The French e-invoicing mandate applies from 1 September 2026 (receiving obligatory for every VAT-liable company; issuing phased: large and mid-sized companies 1 September 2026, SMEs and micro-enterprises 1 September 2027), so every French counterparty has to be checked. ONE call returns the whole agent-side file: legal identity & obligation dates, the computed intra-EU VAT number verified LIVE against VIES, an IBAN FORM check (ISO 13616 structure + mod-97 key) with the bank identified from official registries when iban is supplied, and a deterministic verdict pret_a_facturer (true/false) whose reasons come from a CLOSED list, each tagged blocking or informational and traced to its source. A VIES outage yields an honest informational reason, never a false invalid. Not a payee verification, and the verdict says so where the decision is read: with an iban supplied, verdict.non_verifie sits NEXT TO pret_a_facturer and names what is never checked (the account's existence and the holder's name). An IBAN on a published list of known documentation samples is flagged by the informational reason iban_exemple_documentation, whose absence is not proof of the contrary (the verdict stays green: such an IBAN is well-formed; the account's existence is not tested). The response is Ed25519-signed and carries provenance[] (one entry per block served, with the official register, its licence and its as_of date), so the decision stays auditable offline months later. A SIREN whose administrative status or legal category is missing in Sirene is refused: 404 identite_incomplete (body: siren, champs_absents, fiche), never charged. Partial diffusion (rule diffusion_partielle_nom_retenu_et_compte): a unit not proven to be a legal person has destinataire.denomination null, uncounted; destinataire.information states the partial diffusion. Paid via x402 ($0.03 in USDC or EURC). When you report a result, cite its citation verbatim.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "siren": "<siren>"
    },
    "name": "prepare_french_invoice_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
ibanNoIBAN of the account you are about to pay (spaces and dashes tolerated). Supplying it adds the structure check and the bank identification, and lets the verdict block on iban_invalide; omitting it yields the informational reason iban_non_fourni
sirenYes9-digit SIREN of the French counterparty being checked: the customer you will invoice or the supplier you will pay (digits only, no spaces)

Output Schema

NameRequiredDescriptionDefault
hintNoHow to settle the quote, present when payment_required is true.
quoteNoThe signable x402 payment requirements when payment_required is true: {x402Version, accepts[]} where each entry carries scheme, network, amount, asset and payTo (USDC and EURC options at the same numeric amount). Sign one entry and call again with `x_payment`.
resultatNoThe endpoint's JSON response when payment_required is false. Paid responses carry `source`, `disclaimer` and an Ed25519 signature, and every paid JSON response carries a `provenance` array (all tools since 2026-09-06): one entry per block served, with the official register, licence, version, `empreinte_sha256` (full snapshots), `as_of` date and `precision_as_of` (what that date means), plus the common per-block envelope: `etat` in a closed list (servi, absence_mesuree, absence_non_conclusive, partiel, perime, indisponible, sans_objet), `motif` when unavailable, `age_jours` (only for publication or ingestion dates), `couverture` (complete / partielle / non_mesurable with its measure) and `confiance` in bands (faible / moyenne / forte, only where a measure grounds it, never averaged across blocks). Read the states before the numbers: an absence_non_conclusive, indisponible or partiel block is never « nothing to report »; only absence_mesuree asserts an absence. Register codes: GET /v1/provenance/registres ; states, closed lists and reading rules: GET /v1/lecture (both free). The PDF tools carry no JSON envelope (the PDF report prints it).
free_tierNoFree API key offer for this tool, present with a quote.
payment_requiredYesTrue when this response is an x402 payment quote instead of data: settle one of the quote's `accepts` options and call the tool again with `x_payment`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far beyond the readOnlyHint/openWorldHint annotations, it discloses billing (x402 $0.03 USDC/EURC), a 404 identite_incomplete refusal path with body fields, VIES-outage handling that never yields a false invalid, Ed25519 signing with provenance[] and as_of dates, and what is deliberately never checked (account existence, holder name). This is exactly the behavioural context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The usage trigger is front-loaded correctly and every paragraph is on-topic, but the text is very dense for a two-parameter tool, with heavy parentheticals, all-caps emphasis and mandate-date detail that could be trimmed. Structure is logical but the volume makes skimming harder than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only verification tool with an output schema, the definition covers inputs, refusal modes, partial-diffusion edge cases, pricing, provenance and citation expectations. An agent could invoke and report on it correctly without opening anything else.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so baseline is 3, but the description adds real meaning: supplying iban adds the structure check and bank identification and enables the blocking iban_invalide reason, while omitting it yields iban_non_fourni; a known documentation IBAN triggers iban_exemple_documentation without turning the verdict red. That is added consequence-level semantics, not restatement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb+resource: one call returns an agent-side verification file for a French counterparty (legal identity, VIES-checked VAT, IBAN structure check, deterministic verdict). It even scopes itself negatively ("Not a payee verification"), though it never distinguishes itself from the near-identical sibling prepare_european_invoice_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit trigger conditions are given: onboarding, first invoice, first payment, or changed bank details for a FRENCH counterparty. It also explains iban-supplied vs iban-omitted behaviour. It lacks an explicit when-not or a named alternative tool, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools