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 confir...
Part of the France Data Mcp server.
Free to start. No card required.
AI agents call rpps_search_by_name 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 rpps_search_by_name 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": {
"rpps_search_by_name": {}
}
}See the full France Data Mcp policy for all 36 tools.
These attack patterns abuse exactly the kind of access rpps_search_by_name 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.
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. 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 rpps_search_by_name: 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.
rpps_search_by_name 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 rpps_search_by_name 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 rpps_search_by_name. 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.
rpps_search_by_name 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.