Skip to main content
Glama

French Companies: France API, SIRENE Scraper, SIRET, NAF Code

search_french_companies
Read-only

Search French companies in the official SIRENE register by NAF code, keyword, department, or size to retrieve legal data, headquarters, directors, and optional verified website contacts.

Instructions

French companies from the official SIRENE register by activity (NAF code or keyword), department and size: legal data, headquarters, directors, and optionally a verified website with emails and phones. Pay per result on your Apify account: run start $0.003, company $0.004, website & contacts found $0.025.

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": "search_french_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoCompany name, trade name, director name or address words, e.g. "boulangerie", "plomberie", "Dupont". It matches names, not activity: to get every company of a trade, use NAF codes or sectors below. Optional if you use filters below.
maxItemsNoNo 10,000 cap: large searches are split automatically. Default here: 25.
nafCodesNoe.g. 43.22A (plumbing), 56.10A (restaurants), 62.01Z (software). Full list: insee.fr. Leave empty to use sectors or text search.
departmentsNoDepartment numbers, e.g. 75, 69, 13, 2A. Matches companies having at least one establishment there.
postalCodesNoe.g. 75011, 69003.
createdAfterNoCompany creation date (YYYY-MM-DD). The official API cannot sort by date, so the Actor scans the matching companies (up to 20,000) to find them: narrow with a department or NAF code for brand-new companies.
findContactsNoFor each company, find its website and VERIFY it (the SIREN must appear on the site's legal notice), then extract emails, phones and social links. Billed only when a website is found.
employeeRangesNoEmployee headcount ranges (INSEE).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.3
    • changedInput schema / properties / createdAfter / description
      Previous value: -"Company creation date (YYYY-MM-DD)."New value: +"Company creation date (YYYY-MM-DD). The official API cannot sort by date, so the Actor scans the matching companies (up to 20,000) to find them: narrow with a department or NAF code for brand-new companies."
    • changedInput schema / properties / query / description
      Previous value: -"Company name, trade name, director name or address words, e.g. \"boulangerie\", \"plomberie\", \"Dupont\". Optional if you use filters below."New value: +"Company name, trade name, director name or address words, e.g. \"boulangerie\", \"plomberie\", \"Dupont\". It matches names, not activity: to get every company of a trade, use NAF codes or sectors below. Optional if you use filters below."
  2. First observedv0.1.2

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely useful non-annotation context: it is a paid, per-result Actor billed on the Apify account with concrete prices (run start $0.003, company $0.004, website & contacts $0.025), which materially affects how an agent should size a search. It omits rate limits, run/dataset delivery mechanics, and failure behavior for an open-world scraper.

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

Conciseness5/5

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

Two sentences, zero waste: capability and scope first, cost model second. Both sentences carry information an agent needs before calling, and there is no redundant restatement of the title's keyword list.

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?

All 8 parameters are fully documented in the schema, no output schema exists but the description does enumerate the returned fields, and the cost model is disclosed. What is missing is operational context about how results are delivered for a long-running Apify Actor (run vs. dataset retrieval), which matters for a tool that may split large searches automatically.

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 description coverage is 100%, so the schema already explains every one of the 8 parameters in detail (including the 20,000-company scan caveat for createdAfter and the SIREN-verification rule for findContacts). The description only restates that a website with emails and phones is optional, adding no syntax, defaults, or interaction rules beyond the schema, so the baseline of 3 applies.

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

Purpose4/5

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

The description names a concrete resource (companies from the official SIRENE register) and the filtering axes it supports (NAF code or keyword, department, size), then lists the returned data (legal data, headquarters, directors, optional verified website with emails and phones). It is clearly distinguishable from search_uk_companies by country/register, though it never names a sibling explicitly.

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

Usage Guidelines3/5

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

Usage context is implied rather than stated: 'by activity (NAF code or keyword), department and size' tells the agent which filters exist, and the schema param descriptions carry explicit routing advice (query matches names, not activity; use NAF codes/sectors for a whole trade). The description itself contains no when-to-use, when-not-to-use, or alternative-tool guidance.

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