Skip to main content
Glama

Advanced company search

advanced_search

Search companies using filters for registry, geography, financials, credit, sanctions, cyber, tech, and public funds, with pagination and country breakdowns.

Instructions

Structured multi-filter company search across registry, geography, sector, size, financials, credit/distress, sanctions, NIS2 and cyber exposure, digital footprint (including tech= for a named technology such as PrestaShop or CookieYes) and public money. Returns a paginated list with a per-country breakdown. Totals are capped at 5000 — pagination.isCapped says when the real number is higher. Check data.unknownFilters in the response: any key listed there was DROPPED, so the result is wider than you asked for. Use for analyst-style queries like 'active SK e-shops on PrestaShop with turnover over €1M and no consent platform detected'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
naceNoSingle NACE prefix match, e.g. '46'
techNoNamed technology, exact match, e.g. 'PrestaShop', 'Shoptet', 'CookieYes'. An unknown name returns 400 with the full list in meta.available — ask for a wrong one once to discover what is detectable.
yearNoFinancial year for period-specific figures
limitNoMax results (default 50, cap 200)
nuts2NoNUTS-2 code
nuts3NoNUTS-3 code, e.g. 'SK042'
orderNoNOT 'sort'. An unrecognised value falls back to turnover_desc silently.
activeNoRegistry active flag (NOT is_active)
offsetNoPagination offset
regionNoRegion NAME only, e.g. 'Košický kraj'. A NUTS code here returns zero — use nuts3.
statusNo
healthyNoShorthand: no bankruptcy, liquidation, restructuring or tax debt
districtNo
has_cvesNo
has_rpvsNoSK register of public-sector partners
has_techNoAny detected technology at all
has_emailNo
has_phoneNo
nis2_tierNoessential | important
legal_formNoLegal form code, e.g. '112' = s.r.o. (SK)
profit_maxNoMaximum annual profit in EUR
profit_minNoMinimum annual profit in EUR
entity_typeNoComma-separated also accepted. Natural persons are gated out of results anyway.
has_websiteNo
is_debarredNoExcluded from public procurement
nace_prefixNoComma-separated NACE prefixes, e.g. '46,47'
nis2_sectorNo
ssl_invalidNo
country_codeNoISO 3166-1 alpha-2, comma-separated for several markets, e.g. 'SK,CZ'
credit_gradeNoComma-separated grade letters, e.g. 'A,B'
employee_maxNoMaximum headcount (NOT employees_max)
employee_minNoMinimum headcount (NOT employees_min)
eu_funds_minNoMinimum EU funds received, EUR
has_tax_debtNo
is_vat_payerNo
municipalityNoTown/city name, e.g. 'Košice'
turnover_maxNoMaximum annual turnover in EUR
turnover_minNoMinimum annual turnover in EUR
contracts_minNoMinimum contract count
employee_sizeNoEmployee size-band code
has_contractsNoHas public procurement contracts
in_bankruptcyNo
is_sanctionedNoNOT 'sanctioned'
nis2_in_scopeNoNOT 'nis2_scope'
terminated_toNoTerminated on or before, ISO date
updated_sinceNoOnly rows changed since this ISO date
established_toNoFounded on or before, ISO date YYYY-MM-DD
has_financialsNo
in_liquidationNo
cyber_score_minNo
terminated_fromNoTerminated on or after, ISO date
credit_score_maxNo
credit_score_minNo
established_fromNoFounded on or after, ISO date YYYY-MM-DD
in_restructuringNo
has_critical_cvesNo
has_offshore_linkNo
Behavior5/5

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

With no annotations, the description carries full burden. It discloses the 5000-result cap, the pagination.isCapped flag, unknownFilters dropping behavior, the 400 error with meta.available for unknown tech, silent fallback for order, and region-vs-NUTS gotcha. This is rich behavioral disclosure.

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?

The description is a single dense paragraph; every clause adds value. It front-loads the core purpose, then packs disambiguation and response behavior without redundancy.

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?

Given 57 parameters and no output schema, the description provides critical operational details: capped totals, per-country breakdown, unknown filter drop behavior, and a realistic query example. It covers the most dangerous pitfalls and is complete for its complexity.

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 covers 67% of params; description adds key semantics beyond schema: tech parameter's exact-match behavior and error payload, unknownFilters meaning, and the 'NOT' reminders for sibling-named fields. It doesn't compensate for every undocumented param but adds crucial context.

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?

The description opens with 'Structured multi-filter company search' and enumerates the filter dimensions (registry, geography, sector, size, financials, credit/distress, sanctions, NIS2, cyber, digital footprint, public money), clearly distinguishing it from simpler siblings like search_companies and lookup_company.

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?

It gives an explicit use case: 'Use for analyst-style queries like...' with a concrete example. It does not name a simpler alternative or state when not to use it, so it falls short of a 5, but the context is clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/juliusgerman/entyrix-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server