Skip to main content
Glama

EU e-invoicing and business checks (EN 16931, Peppol, VAT, sanctions)

Look up a company in EU business registers

lookup_company
Read-onlyIdempotent

Look up a company in official European business registers by name or registry number. country: FR (SIREN), NO (org.nr), FI (Y-tunnus), CZ (ICO), PL (KRS number), EE, SK (ICO or name), or any other ISO code / 'LEI' (GLEIF). Name searches return the exact legal entity first (before branches and similar names). Returns legal name, ID, status/active, address, VAT ID, activity code and official source link. Use to confirm a company exists and is active, find its registry number, or map a name to a VAT ID. Free: basic company search costs 0 units and does not use the free tool-call allowance; it is only rate-limited.

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": {
      "query": "<query>"
    },
    "name": "lookup_company"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of matches to return (default 3).
queryYesCompany name or official registry number (e.g. a French SIREN, Polish KRS or Czech ICO).
countryNoRegister to search: FR, NO, FI, CZ, PL (KRS), EE, SK, another ISO country code, or 'LEI' for GLEIF.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / country / description
      Previous value: -"Register to search: FR, NO, FI, CZ, PL (KRS), EE, another ISO country code, or 'LEI' for GLEIF."New value: +"Register to search: FR, NO, FI, CZ, PL (KRS), EE, SK, another ISO country code, or 'LEI' for GLEIF."
  2. Changed3 schema fields changed
    • addedInput schema / properties / country / description
      Added value: +"Register to search: FR, NO, FI, CZ, PL (KRS), EE, another ISO country code, or 'LEI' for GLEIF."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of matches to return (default 3)."
    • addedInput schema / properties / query / description
      Added value: +"Company name or official registry number (e.g. a French SIREN, Polish KRS or Czech ICO)."
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-structured context: the result field set, the ranking rule that exact legal entities appear before branches and similar names, and the pricing note that searches cost 0 units but are rate-limited.

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

Conciseness4/5

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

Front-loaded with the core action, then scope, then return fields, then use cases, then cost — a sensible information hierarchy with no filler sentences. It is dense, and the country-code parenthetical partially duplicates the schema, which keeps it just below the top score.

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

Completeness5/5

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

With no output schema, the description compensates by enumerating the returned fields (legal name, ID, status, address, VAT ID, activity code, source link). Combined with the ranking rule and cost model, an agent has everything needed to call this correctly and interpret the response.

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 the baseline applies. The description's country list (FR/SIREN, NO/org.nr, FI/Y-tunnus, CZ/ICO, PL/KRS, EE, SK, other ISO codes, 'LEI') largely restates the country parameter's own description, adding little new meaning about accepted formats or limit behaviour.

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 ('Look up a company in official European business registers') and immediately narrows scope to name or registry number lookup across named national registers plus GLEIF/LEI. An agent can tell this apart from VAT validation or KYB siblings without opening the schema.

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?

Gives concrete when-to-use framings: confirm existence/active status, find a registry number, or map a name to a VAT ID. It stops short of naming alternatives (e.g. verify_vat, kyb_check) or exclusions, so routing between this and neighbouring verification tools still requires inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.