Skip to main content
Glama

company_lookup

Read-only

Verify company existence, registration, active status, and good standing in official national registers by exact legal name or registration number.

Instructions

Check a national company register: does this company exist, is it registered, is it active, is it in good standing?

    Use this first for any "is X a real / registered / active company"
    question; it is the cheapest call. One live search of the official
    register, about a second. Returns FOUND / NOT_FOUND / AMBIGUOUS with
    the full register record: legal name, number, status (active /
    inactive), good_standing (overdue filings, strike-off, insolvency),
    legal form, incorporation date, address, VAT number, previous names,
    US registered agent. The name must match exactly (case, punctuation
    and legal-form spelling aside); a look-alike name is NOT_FOUND.
    No sanctions, PEP or adverse-media screening: use kyb_findings.

    Price: EUR 0.01 only when the company is found (the first 100 found
    lookups per account are free); NOT_FOUND costs nothing.

    Countries: GB, FR, CZ, SK, NO, FI, CH, EE, LV, US (by name or number);
    PL, BE, BR by registration_number only. US needs `state` (NY, CO, OR,
    CT, TX, PA, FL).

    Args:
        country: ISO 3166-1 alpha-2 code of the register, e.g. "GB"
        company_name: Exact legal name, e.g. "Tesco PLC". Optional when
            registration_number is given
        registration_number: The register's number (GB company number,
            FR SIREN, CZ / SK ICO, NO orgnr, PL KRS, ...). Matched
            exactly; decides alone when given. Prefer it when known
        state: US only (required there): 2-letter state code
        include: Also return the found company's "officers" (GB, CZ, SK,
            NO, FR) and / or latest "filings" (GB, FR), at no extra cost
    

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>"
    },
    "name": "company_lookup"
  }
}

Input Schema

NameRequiredDescriptionDefault
stateNo
countryYes
includeNo
company_nameNo
registration_numberNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.0

TDQS

A5/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations it discloses latency (~1s), pricing (EUR 0.01 only on FOUND, first 100 free, NOT_FOUND free), the three result states, and the full record contents returned. It also warns that look-alike names return NOT_FOUND and enumerates which countries accept name vs number only, which annotations cannot convey.

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?

Front-loads the routing rule and cheapest-call claim before the record details, then separates coverage, Args and pricing into scannable blocks. Long but dense with decision-relevant facts; no filler sentences.

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?

An output schema exists so return structure needn't be restated, yet the description still names FOUND/NOT_FOUND/AMBIGUOUS and summarizes the record fields. Country/state coverage, exact-match behavior, pricing and optional `include` additions are all covered — nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is 0%, so the description carries the full burden and does: each of the five params is documented with format examples (ISO alpha-2, 'GB' company number, FR SIREN, NO orgnr, PL KRS), the US-only `state` requirement with valid codes, the `include` values and which countries support them, and precedence ('registration_number ... decides alone when given').

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 a national company register') plus the exact questions it answers (exists, registered, active, good standing). It explicitly distinguishes itself from kyb_findings for sanctions/PEP/adverse-media work, 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 an explicit priority rule ('Use this first for any "is X a real / registered / active company" question; it is the cheapest call') and names the alternative (kyb_findings) with the condition that selects it. It also states the exact-match constraint and what to prefer when a registration number is known.

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