Low Risk

get_penalties

Return penalty info for Directive 2023/970 violations (Art. 18, 23). Accepts: evg_missing | art7_no_response | art16_no_report. Zwraca informacje o karach za naruszenia Dyrektywy UE 2023/970.

How to control get_penalties ↓

What get_penalties does on Gaproll

AI agents call get_penalties to retrieve information from Gaproll without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
country string
violation_type string

Parameters from the server's own tool schema.

Low Risk

Why get_penalties needs a policy

This tool performs a simple information lookup about potential penalties under EU Directive 2023/970. It retrieves reference data about penalties associated with specific violation categories. There is no indication that it modifies data, deletes records, executes code, triggers external actions, or commits financial transactions.

From the tool's definition Tool name is 'get_penalties' and description states 'Return penalty info' — it retrieves or queries penalty information without modifying, deleting, or executing external operations.

Documented attack patterns abuse exactly the kind of access get_penalties gives an agent:

How to control get_penalties

PolicyLayer is an MCP gateway — it sits between your AI agents and Gaproll, and nothing reaches the server without passing your rules. This is the rule we recommend for get_penalties:

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

get_penalties is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Gaproll — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about get_penalties

What does the get_penalties tool do? +

Return penalty info for Directive 2023/970 violations (Art. 18, 23). Accepts: evg_missing | art7_no_response | art16_no_report. Zwraca informacje o karach za naruszenia Dyrektywy UE 2023/970. It is categorised as a Read tool in the Gaproll MCP Server, which means it retrieves data without modifying state.

What parameters does get_penalties accept? +

get_penalties accepts 2 parameters: country, violation_type. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on get_penalties? +

Register the Gaproll MCP server in PolicyLayer and add a rule for get_penalties: 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 Gaproll. Nothing to install.

What risk level is get_penalties? +

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

Can I rate-limit get_penalties? +

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

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

get_penalties is provided by the Gaproll MCP server (bartek-ywte/gaproll). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Gaproll tool call.

Start from Gaproll, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

3 Gaproll tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.