Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Search French companies by name

search_french_companies
Read-only

Search French companies by name or SIREN in the official INSEE Sirene / INPI RNE registry. Returns top 10 matches with confidence scores and homonym hints to pick the right company.

Instructions

Use FIRST whenever a French company is mentioned by NAME without an identifier. French company search and company lookup by name or SIREN in the official French company registry (INSEE Sirene / INPI RNE data). Returns the top 10 matches, each with a score_confiance (0-1 match confidence) and a correspondance_nom, which together help pick among homonyms; total_results counts every match (tronque: true beyond the 10 served, note_troncature when it is a lower bound). Order: match level first, served as correspondance_nom (exacte: the name, the official name in the French search, equals q once the legal forms written for the result's country are removed at either end of both, never the last word, for the countries of the closed list of written legal forms, a GLEIF result from any other country keeping its whole name; mots_entiers: every remaining word of q is a word of the name; ressemblance: the rest, an acronym or other-field hit included; null if q is a SIREN, SIRET or the result's national ID, or no name is served), then an internal ranking score, not score_confiance (European search: score_confiance before its cap at 1 and its rounding; French search: the similarity of the name, usual name and acronym, plus 0.05 for an active company, the name and acronym only in the real-time fallback); ties: by SIREN in the French search, one country in turn in the European search (rank by national ID within each country, then country code). etages_abandonnes is always present: an empty array means the top 10 is complete; a non-empty one (with resultats_partiels: true) means the local index was degraded and the real-time fallback failed, so the list is partial: retry in a few seconds. If aucune_correspondance_fiable is true, no result resembles the name you asked for (best confidence < 0.5): do NOT treat the top hit as the company; check the spelling or retry. In the local index, typo tolerance only covers active companies under full disclosure: a ceased company, or one under partial disclosure, is found there by its exact name, its beginning or all its words. Partial diffusion (rule diffusion_partielle_nom_retenu_et_compte): a name search leaves out a unit not proven to be a legal person, uncounted (total_results lowered); a SIREN or SIRET search serves it with denomination null, counted in ecartes.diffusion_partielle. Paid via x402 ($0.002 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": {
      "q": "<q>"
    },
    "name": "search_french_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesCompany name, or a French identifier (SIREN, SIRET, VAT number); spaced or labelled ("SIREN : 552 032 534") is fine, it resolves directly. Unsupported characters are stripped, not rejected.

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?

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavior: top-10 truncation, confidence fields, ordering rules, fallback degradation, partial-diffusion handling, and x402 payment. It also warns not to trust the top hit when aucune_correspondance_fiable is true, and it does not contradict the annotations.

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

Conciseness2/5

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

The opening is front-loaded and purposeful, but the body is a dense wall of nested parenthetical rules and edge cases. Much of the detail is relevant, yet the structure makes it hard to scan and is far from concise.

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 one-parameter search with an output schema, the description is more than complete: it covers truncation, confidence, ordering, fallback, partial diffusion, and citation requirements. An agent has enough context to call and interpret it correctly.

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?

Schema coverage is 100% and the single q parameter is already documented as name or SIREN/SIRET/VAT with character stripping. The description reinforces identifier behavior and partial-diffusion effects but adds little parameter-level meaning beyond 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 opens with a specific verb and resource ('French company search and company lookup by name or SIREN') and names the official registry (INSEE Sirene / INPI RNE). It also distinguishes the primary case from identifier-based lookup by saying to use it first when a French company is named without an identifier.

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?

It gives a clear priority rule ('Use FIRST whenever...') and the condition (name without identifier), which is strong when-to-use guidance. It does not name a specific alternative sibling or state when not to use it, so it falls short of full alternatives/exclusions.

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