Skip to main content
Glama

Company Register Search

company_register_search
Read-onlyIdempotent

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 Companies Registration Office (IE), the US STATE business registers (one per state the sos-entities pack covers; pass country "US", optionally with a two-letter state), and the GLEIF LEI crosswalk, which reaches jurisdictions we have no register pack for (DE, SE, AU, SG...). US EXAMPLE: {name: "IPQualityScore LLC", country: "US", state: "FL"} returns the Florida entity number. A US company is formed in ONE state and may also be registered as a FOREIGN entity in others, so without state every covered state register is searched and the several registrations of one company come back as ONE match, which says whether the register it names is the company's own or a foreign registration and names the state it was formed in (Browserbase Inc. is a Delaware corporation found in New York). A state we hold no register for (Delaware, California) is SAID so, with the covered states listed in state_coverage, and the covered registers are searched for foreign registrations of a company formed there. For US public companies prefer resolve_entity (CIK + ticker + FIGI). THIS TOOL REFUSES TO GUESS, and that is its point: when two different companies match a name equally well it answers match_status: "ambiguous" with BOTH, rather than naming one. A one-word trading name usually IS ambiguous — "Bolt", "Apple", "Next", "Sea", "DNB" each match a well-known group AND unrelated micro-entities whose registered name is exactly that word — so pass country when you know it. Every response names EVERY register it asked under searched[], with that register's own as-of date and row count, and a register that could not be reached carries an error there rather than reading as zero rows: "we could not ask Companies House" is never the same answer as "this company is not in Britain". related[] holds entities that collapsed INTO the match — the same company seen through another register, or another country's arm sharing its LEI — so a multinational returns one answer rather than tying with itself. NOT A PEOPLE SEARCH: sole traders and other natural persons are excluded on the publisher's own legal-form field, never guessed from the shape of a name. resolve_entity shares this matcher and returns these register fields too, but searches the US state registers only through this tool.

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": "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). A state we hold a register for narrows the search to that register alone. A state we do not (Delaware, California) is reported in `state_coverage` with the covered states named, and every covered register is 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. Changed3 schema fields changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "country": "NO",
      -    "name": "Equinor ASA"
      -  },
      -  {
      -    "country": "JP",
      -    "name": "株式会社花王"
      -  },
      -  {
      -    "country": "EE",
      -    "name": "Bolt"
      -  }
      -]New value: +[
      +  {
      +    "country": "NO",
      +    "name": "Equinor ASA"
      +  },
      +  {
      +    "country": "JP",
      +    "name": "株式会社花王"
      +  },
      +  {
      +    "country": "EE",
      +    "name": "Bolt"
      +  },
      +  {
      +    "country": "US",
      +    "name": "IPQualityScore LLC",
      +    "state": "FL"
      +  },
      +  {
      +    "country": "IE",
      +    "name": "Roadstone Limited"
      +  }
      +]
    • changedInput schema / properties / country / description
      Previous value: -"OPTIONAL ISO 3166-1 alpha-2 of the register you mean (\"GB\", \"NO\", \"FI\", \"FR\", \"JP\", \"EE\", \"BR\"). Narrows the fan-out, and is frequently the difference between an answer and `ambiguous` on a short name. The GLEIF crosswalk is asked whatever you pass, because for several jurisdictions it is the only register we can name at all."New value: +"OPTIONAL 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."
    • addedInput schema / properties / state
      Added value: +{
      +  "description": "OPTIONAL two-letter US state (\"FL\", \"NY\", \"CO\"...), with country \"US\" (implied when country is absent). A state we hold a register for narrows the search to that register alone. A state we do not (Delaware, California) is reported in `state_coverage` with the covered states named, and every covered register is searched for foreign registrations of a company formed there. Omit to search every covered state register.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, non-destructive and open-world, but the description adds substantial behavior the annotations cannot: refusal to guess with `match_status: "ambiguous"`, `searched[]` with per-register as-of dates and error entries, and `related[]` collapsing cross-register duplicates. The distinction between 'register unreachable' and 'zero rows' is exactly the kind of disclosure an agent needs.

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?

The core purpose is front-loaded and most of the length is load-bearing detail about ambiguity, US state fan-out, and error semantics. It is dense and repetitive in places — the register list appears twice and the capitalized emphasis is heavy — but nothing is filler.

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?

For a fan-out search with no output schema, the description fully specifies the response shape (match_status, searched[], related[], state_coverage) and the coverage limits per jurisdiction. An agent could call this correctly and interpret the result without further documentation.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description goes slightly further with a concrete parameterized example ({name, country, state} returning a Florida entity number) and the advice to pass `country` to break ties. It does not add syntax beyond the schema, which already documents verbatim names and state fallbacks.

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 get the register's own id back') and enumerates the identifier forms returned. It also explicitly distinguishes itself from resolve_entity, so an agent can route without opening either schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use ('when you want the OFFICIAL REGISTERED ENTITY'), when to prefer an alternative ('For US public companies prefer resolve_entity'), and an exclusion ('NOT A PEOPLE SEARCH'). It also advises passing `country` when a short trading name like 'Bolt' is likely ambiguous.

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.