Skip to main content
Glama

NS Pros MCP Gateway

npi-registry__company_register_search

Search the NATIONAL BUSINESS REGISTERS by company name and get the register's own id back, a Companies House number, a Norwegian organisasjonsnummer, a Finnish business id, a SIREN, a Japanese corporate number, an Estonian registry code, a CRO number, a CNPJ, a US state entity number, or an LEI. Use this when you want the OFFICIAL REGISTERED ENTITY. Registers searched: Companies House (GB), Enhetsregisteret (NO), PRH/YTJ (FI), Sirene (FR), 法人番号公表サイト (JP), RIK e-Business Register (EE), the Compan

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "Equinor ASA",
      "country": "NO"
    },
    "name": "npi-registry__company_register_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe company name as you have it, in its own script. Pass it VERBATIM, do not strip the legal form ("Oyj", "AS", "株式会社", "Ltd"): in Japanese the form is a PREFIX as often as a suffix and 株式会社花王 and 花王株式会社 are DIFFERENT companies, so the form is often the only evidence that separates two candidates. Diacritics, full-width characters and kana are all handled.
limitNoMaximum candidates to return, 1-50 (default 10). Does not change which registers are asked, only how many rivals come back.
stateNoOPTIONAL two-letter US state ("FL", "NY", "CO"...), with country "US" (implied when country is absent). It means the state where the company is registered or was formed, not where it is headquartered: a Delaware company headquartered in California is "DE", and passing its headquarters state asks a different question (omit `state` if you only know the headquarters). A state we hold a register for narrows the search to that register alone. A state we do not (Delaware, California) is answered from GLEIF and SEC EDGAR, with the coverage stated in `state_coverage`, and every covered register is also searched for foreign registrations of a company formed there. Omit to search every covered state register.
countryNoOPTIONAL ISO 3166-1 alpha-2 of the register you mean ("GB", "NO", "FI", "FR", "JP", "EE", "IE", "US", "BR"). Narrows the fan-out, and is frequently the difference between an answer and `ambiguous` on a short name. The Irish register and the US state registers are asked ONLY when you pass "IE" or "US". The GLEIF crosswalk is asked whatever you pass, because for several jurisdictions it is the only register we can name at all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does substantial work: it discloses the fan-out across named registers, that GLEIF is always queried, that Delaware/California fall back to GLEIF and SEC EDGAR with coverage reported in `state_coverage`, and that results may be `ambiguous`. It omits rate limits, auth, and (partly due to truncation mid-sentence) the response shape beyond the identifier types.

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

Conciseness3/5

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

The purpose and usage statements are front-loaded and useful, but the ten-item identifier enumeration makes the opening sentence unwieldy, and the register list is cut off mid-word ("the Compan"). It reads as a long run-on rather than a tight, scannable definition.

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

Completeness3/5

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

For a four-parameter tool with no annotations and no output schema, the description covers registers, coverage reporting, and ambiguity but is truncated before finishing the register list and never describes what a returned hit contains or how candidates are ranked. It is adequate rather than complete.

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 description coverage is 100%, so the baseline is 3; the description adds only modest framing, notably that `country` "narrows the fan-out" and is often the difference between an answer and `ambiguous`. The per-parameter nuances (verbatim legal forms, registered-vs-headquarters state) live in the schema, not the description.

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 ("Search the NATIONAL BUSINESS REGISTERS by company name") and enumerates exactly what comes back (Companies House number, organisasjonsnummer, SIREN, CNPJ, LEI, etc.), plus a decision cue: "Use this when you want the OFFICIAL REGISTERED ENTITY." An agent can distinguish this from a GLEIF-style lookup because the description explicitly notes the GLEIF crosswalk is only one of the registers consulted.

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 a clear positive selection condition (official registered entity) and the country/state caveats that change the search: IE and US registers are asked only when those codes are passed. It does not name a concrete alternative tool or state when NOT to use it, so it falls short of the top band.

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.