Skip to main content
Glama

France Company Leads: SIREN, Directors, Revenue

france_company_leads
Read-only

Search the official French company register to build B2B lead lists by activity, area, headcount, revenue or label, and get SIREN, VAT, NAF codes and directors for each company.

Instructions

Search French companies in the official government company directory (recherche-entreprises.api.gouv.fr: INSEE SIRENE + INPI RNE, Licence Ouverte) and get SIREN, head-office SIRET, intra-EU VAT number, NAF activity code and label, legal form, headcount band, SME/mid-size/large category, creation date, head-office and matching local site address, published revenue and net income, directors and official labels (RGE, Bio, Qualiopi and others). Unlike eu_ted_tenders (EU procurement notices) and local_business_leads (OpenStreetMap shops), this is the French company register. Use when sales, agencies, recruiters or market researchers need French B2B lists by activity, area, size or revenue, or the president or gérant of a company. Do not use for other countries, for emails or phones (not in the source) or for sole traders unless includeSoleTraders is set. Parameters: query (free text: name, brand or director); nafCodes (e.g. 62.01Z software, 43.22B plumbing), sectors, departments (e.g. 69, 75, 2A), postalCodes and regions narrow the area and activity; headcountBands, companyCategories (PME, ETI, GE) and legalForms set size and form; revenueMin/revenueMax and netIncomeMin use published accounts; labels keeps certified firms; createdAfter/createdBefore filter by creation date; requireDirector and requireFinancials drop incomplete rows; onlyActive (default true); maxResults caps billed companies. Companies that opted out of prospecting are always excluded and never billed; runs with no matches are free. Returns per item: agentSummary, siren, siretHq, name, tradeNames, vatNumber, nafCode, nafLabel, legalForm, headcountBand, companyCategory, createdOn, hqAddress, hqPostalCode, hqCity, hqDepartment, revenueEur, netIncomeEur, financialYear, directors, topDirectorName, topDirectorRole, labels, annuaireUrl; plus FRBIZ_XLSX (with Directors sheet)/CSV.

Behavior: read-only; runs the Apify Actor pandadad0214/france-company-leads (https://apify.com/pandadad0214/france-company-leads) on your own Apify account. Price: $0.002 per company returned. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "france_company_leads"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoSearch text. Optional free text: company name, brand, address words or a director name, e.g. boulangerie, transport, Dupont. Leave empty to list by filters only.
labelsNoOfficial labels. Keep companies holding any of these labels.
regionsNoRegions. INSEE region codes, e.g. 11 (Ile-de-France), 84 (Auvergne-Rhône-Alpes), 93 (Provence-Alpes-Côte d'Azur), 75 (Nouvelle-Aquitaine).
sectorsNoSectors (NAF sections). Broad sector letters. Empty = any.
nafCodesNoNAF / APE activity codes. French activity codes, e.g. 62.01Z (software), 43.22B (plumbing/HVAC), 56.10A (restaurants), 69.20Z (accountants), 41.20A (house building). Dots optional.
legalFormsNoLegal form codes. INSEE nature juridique codes, e.g. 5710 (SAS), 5720 (SASU), 5499 (SARL), 5498 (EURL), 5599 (SA), 6540 (SCI), 9220 (association).
maxResultsNoMaximum results. You pay per company returned, so this also caps the cost. Default 200; the source allows 10,000 matches per query.
onlyActiveNoOnly active companies. Default on (etat administratif A).
revenueMaxNoMaximum revenue (EUR). Upper turnover bound.
revenueMinNoMinimum revenue (EUR). Only companies that published accounts with at least this turnover.
departmentsNoDepartments. Department codes, e.g. 75 (Paris), 69 (Rhône/Lyon), 13 (Bouches-du-Rhône/Marseille), 33 (Gironde/Bordeaux), 2A. Matches any establishment in the department.
postalCodesNoPostal codes. 5-digit postal codes, e.g. 75011, 31000.
createdAfterNoCreated on or after. Optional YYYY-MM-DD post-filter on company creation date (checked over up to 10,000 matches; combine with narrow filters).
netIncomeMinNoMinimum net income (EUR). Only companies with at least this published net result.
createdBeforeNoCreated on or before. Optional YYYY-MM-DD post-filter.
run_max_itemsNoOptional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
headcountBandsNoEmployee bands. INSEE headcount bands. Empty = any.
requireDirectorNoOnly with a named director. Keep companies that list at least one director (gérant, président...).
run_timeout_secsNoOptional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
companyCategoriesNoCompany size category. PME (SME), ETI (mid-size), GE (large).
requireFinancialsNoOnly with published revenue. Keep companies whose latest accounts show a revenue figure.
includeSoleTradersNoInclude sole traders (entrepreneurs individuels). Default off: sole traders are people; most B2B lists skip them.
run_max_charge_usdNoOptional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true, idempotentHint=false), yet the description adds cost and billing behavior ($0.002 per company, no-match runs free, opted-out companies never billed), a per-call spending cap, timeout expectations and the run_max_items vs maxResults billing interaction. It also discloses that it runs an external Apify Actor on the caller's own account, which is behavior no annotation conveys.

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?

Structure is strong and front-loaded: purpose, then differentiation, then use/do-not-use, then parameters, then behavior and pricing. The mid-section that re-enumerates every parameter is largely redundant with the 100%-covered schema and inflates length, but every other sentence carries non-obvious information.

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 23-parameter tool with no output schema, the description compensates fully by enumerating each returned item field (agentSummary, siren, siretHq, vatNumber, revenueEur, directors, topDirectorName, annuaireUrl, plus XLSX/CSV variants) and the JSON envelope {actor, count, items}. Cost, timeout, and truncation behavior are all stated, so nothing an agent needs to call it safely is missing.

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 all 23 parameters and a baseline of 3 applies. The description goes further by explaining parameter interactions the schema states only partially — that revenue filters rely on published accounts, that createdAfter/createdBefore are post-filters checked over up to 10,000 matches, and that run_max_items fills maxResults when unset and therefore also limits billing.

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?

Opens with a specific verb and resource ("Search French companies in the official government company directory") and names the exact upstream sources (INSEE SIRENE + INPI RNE). It lists the distinctive returned fields (SIREN, VAT, NAF, directors, labels) and explicitly contrasts itself with two siblings, eu_ted_tenders and local_business_leads, so an agent can route without opening a 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?

Gives both positive triggers ("Use when sales, agencies, recruiters or market researchers need French B2B lists by activity, area, size or revenue, or the president or gérant of a company") and explicit exclusions (other countries, emails/phones which are absent from the source, sole traders unless includeSoleTraders is set). This is the when/when-not/alternatives pattern at full strength.

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