Skip to main content
Glama
cturkieh

France Data MCP

by cturkieh
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

etablissement_by_siret

Read-onlyIdempotent

Look up a specific establishment by SIRET. Returns legal name, trade name, NAF code, establishment status, complete address, and workforce range from the official INSEE SIRENE database.

Instructions

Récupère le détail d'un établissement par son SIRET (14 chiffres) via l'API SIRENE INSEE V3.11 : raison sociale de l'unité légale, enseigne commerciale, NAF de l'établissement, dates de création/fermeture, statut administratif actif/fermé, adresse complète, tranche d'effectif. Source : SIRENE INSEE V3.11 (api.insee.fr).

Format de retour : objet LookupResult discriminé par found.

  • found: true → établissement à plat (siret, siren, actif, dateFermeture, enseigne, adresse, …)

  • found: false → { found: false, key, lookupStatus: 'not_found', message }. Cas typiques : clé INSEE_SIRENE_API_KEY non configurée côté serveur (message explicite), SIRET inexistant SIRENE, diffusion partielle INSEE.

⚠️ Différence avec entreprise_by_siren : ce tool renvoie UN établissement précis (un site), alors que entreprise_by_siren renvoie l'unité légale + sa liste d'établissements. Pour détecter un SIRET fermé encore listé actif côté FINESS, lire actif: false + dateFermeture.

Pas de coords : l'endpoint INSEE /siret/<siret> ne renvoie pas les coordonnées GPS. Pour géolocaliser, croiser avec geocode_adresse côté caller ou utiliser entreprises_in_radius.

Rate limit INSEE : 30 req/min (retry-after géré côté serveur).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
siretYesSIRET exact, 14 chiffres.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
foundYes
lookupStatusYes
keyNoClé recherchée (SIREN, num_finess, code INSEE, …).
messageNoExplication actionnable quand `found=false` (cause probable + remédiation).

Tool Definition Quality

A4.6/5.0
Behavior5/5

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

Description greatly augments annotations: details the discriminated return type (LookupResult with found/not_found cases), error handling (missing API key, not found), and rate limiting (30 req/min with retry-after). Also explicitly states no GPS coords. Annotations already declare read-only and idempotent, and description adds expected behavioral context.

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?

Well-structured: purpose, return format, sibling comparison, caveats. Every sentence adds value, though the detailed examples could be shortened slightly. Front-loaded with purpose.

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 tool's simplicity (one param, no nested objects, output schema present), the description covers all necessary context: return types, error cases, rate limits, relation to siblings, and practical usage tips. No gaps remain.

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 covers the single parameter (siret) with description 'SIRET exact, 14 chiffres.' The tool description repeats this without adding new meaning (e.g., validation rules, defaults). With 100% schema coverage, baseline is 3; no additional parameter insight provided.

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 explicitly states it retrieves establishment details by SIRET, listing specific fields (raison sociale, NAF, dates, statut, adresse, effectif). It distinguishes from sibling 'entreprise_by_siren' (legal unit vs site) and 'geocode_adresse' (no coords), making the purpose unmistakable.

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?

Provides clear when-to-use (single establishment lookup) and when-not (GPS retrieval, legal unit search). Explicitly contrasts with 'entreprise_by_siren' and 'geocode_adresse' and includes a detection scenario for closed FINESS sites. Also notes rate limits are handled server-side.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cturkieh/france-data-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server