Karpata – company data from public registers

Check VAT risk (live)

check_vat

Live VAT risk before paying a supplier: SK §81 list and published accounts, CZ unreliable VAT payer (§109) and published accounts, PL white list (with date and account), RO inactive taxpayer. Stored as a verification record (see get_record). Costs credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "country": "<country>",
      "regNo": "<regNo>"
    },
    "name": "check_vat"
  }
}

Input Schema

Name	Required	Description
`date`	No	PL only: the day to check, YYYY-MM-DD.
`regNo`	Yes	Registration number: IČO (SK, CZ), NIP or KRS number (PL), CUI (RO).
`account`	No	PL only: the bank account (NRB) to check.
`country`	Yes	Country code.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 31, 2026

changedInput schema / properties / country / enum

Previous value: -[
-  "SK",
-  "CZ",
-  "RO"
-]New value: +[
+  "SK",
+  "CZ",
+  "PL",
+  "RO"
+]

changedInput schema / properties / regNo / description

Previous value: -"Registration number: IČO (SK, CZ), CUI (RO)."New value: +"Registration number: IČO (SK, CZ), NIP or KRS number (PL), CUI (RO)."

First observedOct 24, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds real context beyond the annotations: the data is live/external (matching openWorldHint), the call is persisted as a verification record (explaining readOnlyHint=false), and it 'costs credits' — billing information an agent cannot get from structured fields. Rate limits, caching, and failure behavior for unavailable registries are not disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the purpose, then the country coverage, then the two operational facts (record persistence, credit cost). No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still tells the agent the result is queryable via get_record, which compensates for the missing return-value section. What the immediate response contains (risk flags vs. a record id) is only implied, and multi-country partial-failure behavior is unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter is already documented, including the PL-only scoping of 'date' and 'account'. The description's '(with date and account)' merely restates the schema constraint, adding no format or semantics beyond it — baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('check VAT risk') and enumerates exactly what is looked up per country (SK §81 list, CZ §109 unreliable payer, PL white list, RO inactive taxpayer). This is clearly distinguishable from generic siblings like get_risk or verify_company because it names the concrete registries queried.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'before paying a supplier' gives a clear triggering context, which is stronger than most sibling tools. However, it never contrasts itself with get_risk or verify_company, so an agent choosing between the three risk-related tools still has to guess.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Karpata – company data from public registers tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?