Low Risk

inspect_site

Vue 360 d'un établissement de santé en 1 appel (V0.10). Pendant naturel de panorama_sante_territoire côté site : agrège en parallèle (a) identification FINESS DREES (raison sociale, adresse, téléphone), (b) statut administratif SIRENE via le resolver SIRET (verdicts site + groupe, best_match, SIR...

Part of the France Data Mcp server.

inspect_site is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE FRANCE DATA MCP →

Free to start. No card required.

AI agents call inspect_site 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 inspect_site 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.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "inspect_site": {}
  }
}

See the full France Data Mcp policy for all 36 tools.

Get this rule live on your own France Data Mcp server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY FRANCE DATA MCP →

View all 36 tools →

These attack patterns abuse exactly the kind of access inspect_site gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so inspect_site only ever does what you allow.

SECURE FRANCE DATA MCP →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the inspect_site tool do? +

Vue 360 d'un établissement de santé en 1 appel (V0.10). Pendant naturel de panorama_sante_territoire côté site : agrège en parallèle (a) identification FINESS DREES (raison sociale, adresse, téléphone), (b) statut administratif SIRENE via le resolver SIRET (verdicts site + groupe, best_match, SIREN explorés, dinum_errors, explication LLM-friendly), (c) professionnels rattachés via num_finess (sample borné + flag truncated si le site a plus de PS — PAS un count total), (d) historique INSEE (timeline périodes administratives par SIRET candidat). Remplace 3 appels MCP individuels (verifier_site_actif + rpps_dans_etablissement + historique_etablissement) par 1 seul. Utile pour : prospection (qualifier un site avant outreach), audit territorial (cross-check rapide d'un FINESS suspect), enrichissement CRM en batch. Format de retour : objet LookupResult. Quand found: true, payload avec 4 sections (finess, statut_site, professionnels, historique). La section historique peut être available: false quand le FINESS existe mais qu'aucun SIRET candidat n'a été identifié (RPPS vide + DINUM 0 match) — dans ce cas le message reprend celui de historique_etablissement. Quand num_finess est absent de FINESS DREES, retourne {found: false, lookupStatus: 'not_found', message}. Coût : 3 sous-appels parallèles. Cache PostgreSQL absorbe la duplication FINESS-RPC ; le pivot RPPS→DINUM est exécuté en double (verifier + historique partagent la cascade), surcoût p95 ≤ 600 ms — acceptable pour un agrégateur. Pour les besoins ciblés (juste le verdict, juste l'historique), préférer les tools individuels. Payload lourd (~7K tokens) : passer historique_detail: false pour un retour allégé (résumé au lieu des timelines SIRENE complètes) en usage batch. Alias acceptés : numFiness/finess/id → num_finess.. It is categorised as a Read tool in the France Data Mcp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on inspect_site? +

Register the France Data MCP server in PolicyLayer and add a rule for inspect_site: 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.

What risk level is inspect_site? +

inspect_site is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit inspect_site? +

Yes. Add a rate_limit block to the inspect_site 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.

How do I block inspect_site completely? +

Set action: deny in the PolicyLayer policy for inspect_site. 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.

What MCP server provides inspect_site? +

inspect_site 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.

Enforce policy on every France Data Mcp tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.