Low Risk

list_unreliable_payers

Return the full list of currently unreliable Czech VAT payers from ADIS. WARNING: response can be 50–100 MB (tens of thousands of entries). Intended for daily mirroring into a local database, not for ad-hoc inspection. For "is this specific company unreliable?" use check_dph_payer instead.

Part of the Adis server.

list_unreliable_payers 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 ADIS →

Free to start. No card required.

AI agents call list_unreliable_payers to retrieve information from Adis 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 list_unreliable_payers 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": {
    "list_unreliable_payers": {}
  }
}

See the full Adis policy for all 3 tools.

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

ENFORCE ON MY ADIS →

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

SECURE ADIS →

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

What does the list_unreliable_payers tool do? +

Return the full list of currently unreliable Czech VAT payers from ADIS. WARNING: response can be 50–100 MB (tens of thousands of entries). Intended for daily mirroring into a local database, not for ad-hoc inspection. For "is this specific company unreliable?" use check_dph_payer instead.. It is categorised as a Read tool in the Adis MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_unreliable_payers? +

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

What risk level is list_unreliable_payers? +

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

Can I rate-limit list_unreliable_payers? +

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

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

list_unreliable_payers is provided by the Adis MCP server (@czagents/adis). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Adis tool call.

Deterministic rules across all 3 Adis 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.