Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Prepare Belgian or Polish invoice file

prepare_european_invoice_file
Read-only

Verify a Belgian or Polish supplier before invoicing or payment: confirm official registry identity, VAT via VIES, and Polish White List IBAN declarations, with a signed, auditable verdict.

Instructions

Use when the company you are about to invoice or pay is BELGIAN or POLISH and you must verify the supplier before payment (for France, use prepare_french_invoice_file). ONE call returns official registry identity, the VAT number checked against VIES (Belgium's structured B2B e-invoicing mandate has been in force since 1 January 2026) and, uniquely in Poland, whether the IBAN is actually DECLARED by that taxpayer in the official White List (wykaz podatnikow VAT). The Polish check has FISCAL scope: paying more than 15,000 PLN into an undeclared account costs the buyer the deduction and creates joint liability for the supplier's VAT (art. 117ba Ordynacja podatkowa), so an undeclared account is a blocking reason. Everywhere else the bank leg is a FORM check (ISO 13616 structure + mod-97 key) plus bank identification, never a payee verification: with an iban supplied, verdict.non_verifie sits next to the verdict and names what is not checked (account existence, holder name), and the White List itself proves the account is DECLARED by that taxpayer, never who holds it. Returns a deterministic pret_a_facturer verdict with closed-list reasons, each tagged blocking or informational. In Poland, a taxpayer without a KRS number (a CEIDG sole trader, or an undecided case) gets these checks without its name or address, the omission counted in ecartes; so do, in Belgium, an entity without legal form (a natural-person enterprise) or of a form without legal personality, and in Poland a KRS entity of an undecided form (a foreign entrepreneur's branch). The response is Ed25519-signed and carries provenance[]: one entry per block served, with the official register, its licence and its as_of date, the White List entry carrying the date actually sent to the ministry's API, so the payment decision is provable to an auditor offline. 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": {
      "pays": "<pays>",
      "id": "<id>"
    },
    "name": "prepare_european_invoice_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesBelgian enterprise number (10 digits, KBO/BCE) or Polish NIP (10 digits; a KRS number is not accepted, 404 not billed); dots, spaces and dashes are tolerated
ibanNoIBAN of the account you are about to pay, unpunctuated (spaces tolerated); optional, but it is what unlocks the Polish White List account check, and everywhere the structure check plus bank identification
paysYesCountry of the counterparty: BE (Belgium) or PL (Poland). For France use prepare_french_invoice_file.

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

A4.7/5.0
Behavior5/5

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

Annotations only say readOnlyHint and openWorldHint; the description adds substantial behavior the agent could not infer: VIES validation, the Polish White List fiscal scope with the 15,000 PLN / art. 117ba joint-liability consequence, the `non_verifie` field that names what is not checked, the ecartes offsetting for entities without KRS/legal form, the Ed25519 signature and provenance[] with as_of dates, and x402 pricing at $0.03. Nothing here contradicts readOnlyHint — the tool only reads registries and returns a signed verdict.

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?

It is correctly front-loaded with the trigger and the alternative, but it is one dense paragraph with internal repetition — the point that the bank check is a form check and that the White List proves declaration, not ownership, is stated twice in different words. Several clauses (ISO 13616/mod-97, art. 117ba, ecartes, Ed25519) are packed without visual separation, making it hard to scan.

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 3-parameter tool with an output schema, a signature, and country-specific branch logic, the description covers what a caller needs: triggers, country routing, blocking vs informational semantics, the entities for which name/address checks are omitted, provenance and cost. Return-field detail is correctly left to the output schema.

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 100%, so the schema already documents `id`, `iban` and `pays` formats and the BE/PL enum, setting a baseline of 3. The description earns one extra point by explaining what `iban` unlocks functionally (the Polish White List declaration check, otherwise only a structural check) and by tying `pays` to the country-specific omission behavior, which the schema does not convey.

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

Purpose5/5

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

States a specific action (prepare an invoice file / pre-payment supplier verification) for a specific resource (Belgian or Polish counterparties), and explicitly names the sibling it is not for ('for France, use prepare_french_invoice_file'). An agent can separate this from the French variant and from the generic company-profile siblings purely from the text.

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

Usage Guidelines5/5

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

The opening clause gives an explicit trigger condition (the counterparty is BELGIAN or POLISH and you must verify before payment) and routes the France case to a named alternative. It also states a concrete when-not-to-treat-as-failure rule: an undeclared Polish account is 'a blocking reason', whereas elsewhere the bank leg 'is a FORM check... never a payee verification', which tells the agent how to act on the outcome.

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