france-data-mcp

centres_sante_by_finess

Read-onlyIdempotent

Récupère le détail d'un Centre de Santé (CDS) par son numéro FINESS. Différenciateur métier vs etablissement_by_finess : expose carte_vitale, APCV, et spécialités exercées sur place (Annexe A CNAM). Retourne un LookupResult discriminé par found.

found: true → payload CDS complet (raison sociale, accepte_carte_vitale/apcv, specialites.codes/libelles alignés, type_etab 124/125, adresse, coords centroïde commune, telephone). found: false → {found: false, key, lookupStatus: 'not_found', message} quand le numéro FINESS pointe vers une structure non-CDS (hôpital, EHPAD, labo) ou un CDS très récent (CNAM latence ~1 sem).

Source : Annuaire santé Ameli, Assurance Maladie (sync hebdomadaire CNAM, mention obligatoire L.1461-2 CSP). Pour les structures non-CDS, utiliser etablissement_by_finess.

Alias acceptés : numFiness/finess/etab_finess → num_finess.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`num_finess`	Yes	Numéro FINESS exact 9 chiffres. Ex: '750000123'.
`include_freshness`	No	Si true, ajoute un champ `data_freshness` au payload (dans `query_metadata` si présent, sinon à la racine) listant, par source (FINESS, Ameli, RPPS, CDS, IRIS), la dernière ingestion réussie (`last_success_at`, `staleness_days`) ET la dernière fois que la donnée a réellement changé (`last_data_change_at`, `data_age_days` — un run court-circuité « fichier amont identique » compte comme succès mais ne rajeunit pas la donnée ; c'est `data_age_days` qui dit l'âge réel de ce qui est servi). Opt-in pour ne pas alourdir les payloads par défaut. Cache 5min côté serveur — coût négligeable.

Output Schema

TableJSON Schema

Name	Required	Description
`key`	No	Clé recherchée (SIREN, num_finess, code INSEE, …).
`found`	Yes
`message`	No	Explication actionnable quand `found=false` (cause probable + remédiation).
`lookupStatus`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 5, 2026

changedInput schema / properties / include_freshness / description

Previous value: -"Si true, ajoute un champ `data_freshness` au payload (dans `query_metadata` si présent, sinon à la racine) listant la dernière ingestion réussie par source (FINESS, Ameli, RPPS, CDS) avec `staleness_days`. Opt-in pour ne pas alourdir les payloads par défaut. Cache 5min côté serveur — coût négligeable."New value: +"Si true, ajoute un champ `data_freshness` au payload (dans `query_metadata` si présent, sinon à la racine) listant, par source (FINESS, Ameli, RPPS, CDS, IRIS), la dernière ingestion réussie (`last_success_at`, `staleness_days`) ET la dernière fois que la donnée a réellement changé (`last_data_change_at`, `data_age_days` — un run court-circuité « fichier amont identique » compte comme succès mais ne rajeunit pas la donnée ; c'est `data_age_days` qui dit l'âge réel de ce qui est servi). Opt-in pour ne pas alourdir les payloads par défaut. Cache 5min côté serveur — coût négligeable."

Changed1 schema field changedMay 15, 2026

addedInput schema / properties / include_freshness

Added value: +{
+  "default": false,
+  "description": "Si true, ajoute un champ `data_freshness` au payload (dans `query_metadata` si présent, sinon à la racine) listant la dernière ingestion réussie par source (FINESS, Ameli, RPPS, CDS) avec `staleness_days`. Opt-in pour ne pas alourdir les payloads par défaut. Cache 5min côté serveur — coût négligeable.",
+  "type": "boolean"
+}

AddedMay 15, 2026

TDQS

A5/5.0

Behavior5/5

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

The description thoroughly explains both success and failure modes: it details the `found: true` payload structure and the `found: false` response with `lookupStatus: 'not_found'` and a message. It also transparently discusses the `include_freshness` parameter, explaining the difference between `last_success_at` and `last_data_change_at` and how short-circuited runs affect data age. This exceeds the annotations (readOnly, openWorld, idempotent) by describing actual runtime behavior.

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?

Although the description is relatively long, every sentence adds necessary information: main purpose, differentiation, success/failure payloads, source, aliases, and the optional freshness parameter. It is well-organized into clear sections and uses formatting (bold, code spans) to aid readability. There is no redundancy or filler.

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?

The description is self-contained: it explains the tool's scope, the distinction from a sibling tool, the exact response shapes for both success and failure, the data source with legal mention, alias handling, and the optional freshness reporting. Given the complexity of the tool (lookup with status, multiple fields, aliases, freshness option), nothing essential is missing for an agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers two parameters (`num_finess` and `include_freshness`), both fully described with types, defaults, and examples. Additionally, the description lists accepted aliases for `num_finess`, which adds practical value beyond the schema. The `include_freshness` parameter is explained in depth, including its behavior with `query_metadata`. Schema coverage is 100% and the description enriches it further.

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 clearly states the tool retrieves details of a Health Centre (CDS) by its FINESS number, and explicitly distinguishes it from the sibling `etablissement_by_finess` by listing the unique fields it exposes (carte_vitale, APCV, specialités CNAM). This makes the tool's purpose unambiguous and differentiated.

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?

The description provides explicit guidance on when to use this tool versus the alternative: 'Pour les structures non-CDS, utiliser `etablissement_by_finess`.' It also mentions the data source and refresh cadence (weekly CNAM sync), and the latency for very recent CDS, giving clear operational context.

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

All france-data-mcp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.