Recherche des Centres de Santé (CDS) dans un rayon géographique (PostGIS ST_DWithin). Source : Annuaire santé Ameli, Assurance Maladie (mention obligatoire L.1461-2 CSP — sync hebdomadaire CNAM). Différenciateur métier vs etablissements_finess_in_radius filtré famille=124 : expose carte_vitale, A...
Part of the France Data Mcp server.
Free to start. No card required.
AI agents call centres_sante_in_radius to retrieve information from France Data Mcp without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though centres_sante_in_radius only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"centres_sante_in_radius": {}
}
}See the full France Data Mcp policy for all 36 tools.
These attack patterns abuse exactly the kind of access centres_sante_in_radius gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Recherche des Centres de Santé (CDS) dans un rayon géographique (PostGIS ST_DWithin). Source : Annuaire santé Ameli, Assurance Maladie (mention obligatoire L.1461-2 CSP — sync hebdomadaire CNAM). Différenciateur métier vs etablissements_finess_in_radius filtré famille=124 : expose carte_vitale, APCV, spécialités exercées sur place (Annexe A nomenclature CNAM, ~70 codes). CDS = structures de soins ambulatoires non lucratives encadrées L.6323-1 CSP (associations, mutuelles, communes, hôpitaux). Volume ~3K en France. Filtres : - specialite_codes : array Annexe A (ex: ['01'] médecine générale, ['53'] dentaire). Match any-of — retourne les CDS qui exercent AU MOINS UNE des spécialités demandées. - accepte_carte_vitale : true / false / omis. Quasi-totalité accepte CV en pratique → filtre surtout utile en false pour audits. - type_etab_codes : ['124'] CDS standard, ['125'] CDS dentaire (deprecated CNAM, en voie d'extinction). Coords = centroïde commune (~3 km moyenne) — pour précision adresse, pivoter via etab_finess retourné avec etablissement_by_finess. PAS d'horaires/tarifs/secteur 1/2 (retirés du nouvel annuaire CNAM post-2025). Alias acceptés : radius/radius_meters → radius_km, latitude/longitude → lat/lon.. It is categorised as a Read tool in the France Data Mcp MCP Server, which means it retrieves data without modifying state.
Register the France Data MCP server in PolicyLayer and add a rule for centres_sante_in_radius: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches France Data Mcp. Nothing to install.
centres_sante_in_radius is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the centres_sante_in_radius rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for centres_sante_in_radius. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
centres_sante_in_radius is provided by the France Data MCP server (france-data-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 France Data Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.