Skip to main content
Glama

france-data-mcp

by io.github.cturkieh

rpps_search_by_name

Read-onlyIdempotent

Trouve un PS par identité (matching trigram tolérant aux accents/typos). Usage : "Dr Martin à Paris" → nom: "Martin", departement: "75". Nom obligatoire ; prenom et departement affinent.

Tri par match_score ∈ [0..1] décroissant (score trigram pg_trgm). Un score <0.5 = homonymie partielle à confirmer côté caller. Sans departement, des homonymes exacts ("Pierre Martin") ont TOUS le même score ~1.0 et ne sont pas départagés — toujours filtrer par dept ou prénom sur un nom commun.

truncated: true = d'autres résultats existent (restreindre, ne pas parcourir).

Chaque résultat géolocalisé porte geo_precision ∈ {"adresse", "etablissement_finess", "centroide_commune"} — lire ce champ pour évaluer la fiabilité des coords (précise BAN/FINESS au m près vs centroïde commune ~3 km, non discriminant intra-commune).

Catégorie par défaut : Civil (C, ~97 % — libéraux, salariés privés, hospitaliers contractuels). Opt-in : include_agents_publics: true ajoute Agents publics (M, ~0,3 % — PH titulaires, ARS, CNAM, Éducation nationale, PMI, militaires SSA) ; include_etudiants: true ajoute Étudiants (E, ~2,5 % — internes, externes, élèves IDE/SF). Réf : https://mos.esante.gouv.fr/NOS/TRE_R09-CategorieProfessionnelle/.

Source : Annuaire Santé, Agence du Numérique en Santé (ANS) — Licence Ouverte v2.0

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nomYesNom de famille (non vide).
limitNoNombre max de résultats (1-500, défaut 100).
prenomNoPrénom du PS.
departementNoCode département INSEE (ex: '75', '2A', '2B', '971'). Métropole 2 caractères (Corse '2A'/'2B', pas '20'), DOM/COM 3 caractères.
include_etudiantsNo
include_freshnessNoSi 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.
include_agents_publicsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNombre d'entrées retournées dans `results` (post-troncature).
totalNoEffectif réel avant troncature. Présent sur les tools de nomenclature paginés (lister_*) : `count` = échantillon, `total` = total réel, re-appeler avec un `limit` supérieur si `truncated`.
resultsYesEntrées métier (shape spécifique au tool, cf. description du tool).
freshnessNoFraîcheur des sources (présent si `include_freshness: true`).
perimetreNoLentille de la source : ce que le comptage inclut/exclut. Lire `completeness_note` et la restituer au lecteur final.
truncatedNotrue si le total réel dépasse `limit` (re-paginer via `offset` si supporté, ou augmenter `limit` sur les lister_*). Optional sur les tools de listing exhaustif (lister_*).
query_metadataNoMetadata de la query (radius_km, departement, filtres appliqués, …).
activite_hebergeeNoCompte juxtaposé des sites hébergeant l'activité correspondant à la famille filtrée, sous une autre catégorie FINESS. Distinct du `count` principal — lire `note` pour comprendre la sémantique et ne JAMAIS additionner les deux comptes sans préciser leur nature.

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already provide readOnlyHint, idempotentHint, etc. Description adds important behavioral details: sorting by match_score, truncation flag, geo_precision field with precision values, category filtering (default Civil with opt-ins for agents publics and étudiants). No contradiction with annotations.

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?

The description is comprehensive but well-structured, with clear sections for usage, sorting, truncation, geo_precision, categories, and source. Each sentence adds value; no redundancy. However, it is relatively long, earning a 4 rather than a 5.

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 complexity (7 parameters, output schema exists, annotations present), the description covers all essential aspects: purpose, usage, behavioral details (sorting, truncation, geo_precision), parameter semantics, categories, and data source. It is sufficient for correct selection and invocation.

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 71%, and description adds context beyond schema descriptions: explains nom is required, departement code format (including Corse and DOM/COM), purpose of include_freshness (adds freshness metadata), and category opt-ins. The example clarifies how nom and departement are used together.

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 finds a healthcare professional by identity using trigram matching tolerant to accents/typos. It provides a concrete example ('Dr Martin à Paris') and distinguishes itself from sibling tools that search by radius or specialty.

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?

Provides explicit guidance on when to use: with example input, clarifies required field (nom) and optional refiners (prenom, departement). Warns about homonyms without departement and suggests filtering. Does not explicitly state when not to use, but context is clear.

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation3/5

While tools have distinct purposes, there is overlap among several similar tools (e.g., multiple professional and establishment search tools). The detailed descriptions help differentiate, but an agent may struggle to choose correctly among them.

Naming Consistency2/5

Naming mixes French and English, with no consistent pattern (e.g., 'enrichir_concurrents' vs 'inspect_site', 'etablissement_by_finess' vs 'etablissements_finess_in_radius'). This inconsistency makes the toolset harder to navigate.

Tool Count3/5

36 tools is high but justified given the broad domain. However, there are multiple tools for similar tasks (e.g., four professional search tools), suggesting some redundancy. The scope is borderline but acceptable.

Completeness4/5

The toolset covers a wide range of needs for French health data analysis: establishments, professionals, population, geocoding, demographics, and composite analyses. Few obvious gaps exist, though some specialized tasks might require additional integration.

Resources