Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

French identity batch: SIREN, SIRET, VAT

get_french_company_identity_batch
Read-only

Batch-validate and enrich French customer or CRM exports by resolving SIREN, SIRET and VAT, checking VIES, and flagging duplicates.

Instructions

Batch identity check of a French customer or CRM file: 2 to 150 lines per call, each a SIREN, SIRET, French VAT number or name|postcode, in file order. Use when a user hands over a customer export, e.g. « Voici mon export clients, complète et corrige SIREN, SIRET et TVA. » or « Enrichis et nettoie ma base CRM : SIREN, TVA, adresse, cessés et doublons. » Per line: resolution (resolu, a_confirmer with up to 5 candidates ranked by score_confiance, introuvable, siren_invalide, siren_inconnu, non_diffusible), SIREN, head-office SIRET, status and cessation date, address, VAT number checked live on VIES (indisponible, never a false invalide), duplicates flagged (doublon_de). VAT checks: in French business hours, VIES serves one verdict every 4 to 5 s and refuses concurrency; before pipelined checks, a full batch had 15 of 262 resolved lines checked; with them, outside business hours (23:51 UTC), 105 of 265; measured 2026-10-08; a line whose check could not start in time says non_verifie, budget_vies_epuise. Never a silent choice: a name is resolved only by a single candidate of the complete index union at its postcode that bears that name (legal name, usual name or acronym), otherwise a_confirmer; natural persons are never served as candidates (counted in candidats_non_servis). With ambiguous names, send 50 lines per call (each a_confirmer line carries its candidates). Request line up to 11000 bytes: about 148 names of 63 characters. With depuis (a past day or today), at most 20 lines per call: each resolu line also carries changements, what changed since that date in BODACC and the local stocks (verdict nouveautes, rien_de_nouveau or lecture_incomplete, totals per type, the 3 latest facts, the window actually read, lecture_complete and the line's blocks not read; stocks stale for that date are named once at the top, in changements.stocks_perimes); any other line says why in motif_sans_changements; billed $0.01 per line. EU tenders and industrial property: get_french_company_updates_since, one company per call. Billed per line at $0.003 via x402, duplicates included; with a verified account's API key (api_key), 100 lines a month are free, and a call of more lines than are left is paid in full. Closed lists: GET /v1/lecture. A full call of this tool costs at most $0.45 (150 lines), $0.20 with depuis (20 lines), within the $1.00 single-payment cap that x402 clients apply by default. 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": {
      "lignes": "<lignes>"
    },
    "name": "get_french_company_identity_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
depuisNoOptional: also each resolved line's changes since this day, a past day or today, at $0.01 per line and 20 lines per call at most. Accepts YYYY-MM-DD (a real date), or a full ISO 8601 timestamp (offset Z, ±HH:MM, ±HHMM or none, read as UTC): only its UTC day is kept.
lignesYes2 to 150 lines (20 with depuis), each a SIREN, a SIRET, a French VAT number (FR + 11 digits) or name|postcode (e.g. "HERMES INTERNATIONAL|75008")

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

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds substantial behavior: resolution statuses, live VIES checking with concurrency/rate limits, failure modes such as non_verifie and budget_vies_epuise, duplicate flags, natural-person exclusion, and depuis change tracking. No annotation contradiction; the only minor gap is that the dense VIES timing benchmark could be harder to parse than necessary.

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

Conciseness4/5

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

The purpose is front-loaded and every major clause conveys relevant operating detail for a genuinely complex batch tool. However, it is a very dense single block with long semicolon-heavy sentences and some repeated pricing/limit details, so structure could be clearer.

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?

Given the complexity and the existing output schema, the description is complete: it covers batch limits, input formats, depuis behavior, failure modes, billing, alternatives, and result statuses. An agent has enough information to select and call the tool correctly.

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% and already documents both parameters, so baseline is 3. The description adds useful operational meaning beyond the schema, including file order, an 11,000-byte per-line limit, and the 50-line recommendation for ambiguous names, though much of the lignes and depuis explanation restates the schema.

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?

The description states a specific verb and resource: 'Batch identity check of a French customer or CRM file,' and enumerates the accepted line types (SIREN, SIRET, VAT, name|postcode) and batch bounds. It is clearly identity-focused and routes EU tenders/industrial property to get_french_company_updates_since.

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?

It gives an explicit use case with examples ('Voici mon export clients...'), operational guidance for ambiguous names (send 50 lines per call), and a named alternative for one-company EU tender/industrial-property checks. The when-to-use guidance is strong and concrete.

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