Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Prepare French e-invoicing recipient

prepare_french_einvoicing_recipient
Read-only

Prepares a compliant French e-invoice recipient record from a SIREN, returning legal identity, VAT number, SIRET addresses, NAF code, and indicative e-invoicing obligation dates for audit-ready use.

Instructions

Use when you need to PREPARE a compliant French e-invoice for a company (invoice header, VAT number, addressing) rather than decide whether paying it is safe; for the full verify-the-supplier-before-payment verdict, IBAN included, call prepare_french_invoice_file. The French e-invoicing mandate applies from 1 September 2026: receiving becomes obligatory for every VAT-liable company on that date, issuing is phased (large and mid-sized companies 1 September 2026, SMEs and micro-enterprises 1 September 2027; art. 91 of the 2024 Finance Act). Returns legal name & form, active/ceased status, computed intra-EU VAT number (+ VIES-check pointer), establishments (SIRET) with addresses, NAF code (with its nomenclature, NAF 2025 code and status) and indicative send/receive obligation dates from the INSEE size category. 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 preparation is auditable offline. Preparation only: Sirenic is not an accredited platform (PDP), does not access the central directory and never issues, transmits or routes invoices, nor confirms PPF/PDP registration. 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 ($0.02 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_einvoicing_recipient"
  }
}

Input Schema

NameRequiredDescriptionDefault
sirenYes9-digit SIREN of the company to be invoiced (digits only, no spaces); use search_french_companies first if you only have a name

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
Behavior4/5

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

Annotations declare only readOnlyHint and openWorldHint; the description supplies the substantive behavior an agent cannot get elsewhere: the response is Ed25519-signed with a provenance[] block per register (licence and as_of date), a partial-diffusion rule that nulls destinataire.denomination for unproven legal persons, and the disclaimer that Sirenic is not a PDP and does not touch the central directory. It also discloses the x402 cost ($0.02 USDC/EURC) and a reporting obligation to cite `citation` verbatim, though it says nothing about failure modes for an invalid SIREN.

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 routing sentence and the alternative are correctly front-loaded, but the body is one undifferentiated run-on paragraph that piles statutory history (art. 91 of the 2024 Finance Act), a verbose field inventory and payment mechanics into a single block. Some detail is duplicative of the output schema, which already documents the returned fields, so not every clause earns its place.

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

Completeness4/5

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

For a one-parameter, read-only preparation tool, the definition covers what is produced, the legal trigger dates, the signing/provenance guarantees, the legal-liability limits and the cost — the elements an agent needs to decide and to caveat its answer. The only real gap is error/empty behavior and the absence of any note on the alternative prepare_european_invoice_file, which the sibling list shows exists.

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

Parameters3/5

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

There is a single parameter and schema coverage is 100%, with the schema itself specifying the 9-digit pattern, digits-only constraint and the 'use search_french_companies first if you only have a name' hint. The description does not add any meaning about the `siren` argument beyond that, so the baseline of 3 applies.

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 verb and resource ('PREPARE a compliant French e-invoice for a company') and immediately enumerates the payload it covers (invoice header, VAT number, addressing), which removes ambiguity about what 'prepare' means here. It also names the sibling it is not (prepare_french_invoice_file, the supplier-verification verdict with IBAN) and the exact payroll-domain return fields, so an agent can route correctly without opening the schema.

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?

Opens with an explicit 'Use when you need X rather than Y' condition and names the concrete alternative call for the excluded case (prepare_french_invoice_file for the verify-before-payment verdict). It adds a temporal trigger (mandate effective 1 September 2026) and a hard boundary ('preparation only... never issues, transmits or routes invoices'), leaving little to inference.

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