Low Risk

rechercher_subvention

Recherche des subventions versees par les collectivites locales et organismes publics. Filtrage par beneficiaire, attribuant, objet, montant minimum et annee. Source : data.gouv.fr (obligation legale > 23 000 EUR).

Part of the Service Public France server.

rechercher_subvention 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 SERVICE PUBLIC FRANCE →

Free to start. No card required.

AI agents call rechercher_subvention to retrieve information from Service Public France 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 rechercher_subvention 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": {
    "rechercher_subvention": {}
  }
}

See the full Service Public France policy for all 38 tools.

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

ENFORCE ON MY SERVICE PUBLIC FRANCE →

View all 38 tools →

These attack patterns abuse exactly the kind of access rechercher_subvention 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 rechercher_subvention only ever does what you allow.

SECURE SERVICE PUBLIC FRANCE →

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

What does the rechercher_subvention tool do? +

Recherche des subventions versees par les collectivites locales et organismes publics. Filtrage par beneficiaire, attribuant, objet, montant minimum et annee. Source : data.gouv.fr (obligation legale > 23 000 EUR).. It is categorised as a Read tool in the Service Public France MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on rechercher_subvention? +

Register the Service Public France MCP server in PolicyLayer and add a rule for rechercher_subvention: 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 Service Public France. Nothing to install.

What risk level is rechercher_subvention? +

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

Can I rate-limit rechercher_subvention? +

Yes. Add a rate_limit block to the rechercher_subvention 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 rechercher_subvention completely? +

Set action: deny in the PolicyLayer policy for rechercher_subvention. 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 rechercher_subvention? +

rechercher_subvention is provided by the Service Public France MCP server (https://mcp-service-public.nhaultcoeur.workers.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Service Public France tool call.

Deterministic rules across all 38 Service Public France 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.