Skip to main content
Glama

Search Polish Companies

search_companies
Read-onlyIdempotent

Search and filter Polish KRS companies (spółki). Compabase also holds the full CEIDG/JDG register; this tool does not browse JDG — those without a public contact email are hidden because of RODO. Default fields=summary returns a compact row (name, NIP, KRS, location, PKD, latest financials, email/phone/website) — small enough for MCP clients. fields=contacts_only is name/NIP/KRS/city/email/phone/website only. fields=full returns every company_search column plus contacts and may exceed client size limits. Use for rankings, sector filters, city/county/region browsing, name search, or NIP/KRS lookup. When a PKD is mostly JDG, a sparse result includes a hint (full CEIDG is in the database; listing is RODO-gated). For a handful of emails or phones, fields=contacts_only here is enough; export_companies is meant for bulk files.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
krsNoKRS number of the company in the Polish National Court Register (10 digits).
nipNoPolish company tax number (NIP) of the business, 10 digits.
pkdNoPrimary PKD code prefix, e.g. '46.90.Z' or '46'.
cityNoCity name — KRS records use uppercase, e.g. 'WARSZAWA', 'POZNAŃ'.
nameNoCompany name, used when the KRS or NIP is not known.
yearNoFilter to companies whose latest financial_period_to falls within this calendar year (e.g. 2024). Use only for sector/ranking browse — omit when looking up a company by name, KRS, or NIP.
limitNoMax results (default: 10, max: 50).
naicsNoDetailed industry: NAICS 6-digit codes, comma-separated (any of them), e.g. '541511,541512'. AI classification of what the company actually does.
nicheNoDetailed industry in words (Polish), matched against the company's niche, e.g. 'opakowania', 'software house', 'catering'.
countyNoCounty / powiat (lowercase).
fieldsNoResponse size. Default summary (name, NIP, KRS, location, PKD, latest financials, email/phone/website). contacts_only: name, NIP, KRS, city, email, phone, website. full: every company_search column plus contacts — often too large for MCP clients.
regionNoVoivodeship (lowercase), e.g. 'mazowieckie', 'wielkopolskie'.
all_pkdNoMatch any PKD code in the company's activity list (not just primary).
serviceNoService the company offers (Compabase services dictionary, from company websites): service name in Polish/English/German, e.g. 'księgowość', 'heat pumps', or slugs from compabase.com/services, comma-separated (any of them).
sort_byNoSort field (default: revenue_total). registration_date + sort_dir=desc lists the newest registrations first. revenue_growth_pct + sort_dir=desc lists the fastest-growing companies (y/y revenue growth from KRS financial statements; combine with revenue_min to skip small companies).
currencyNoCurrency for monetary filters. Default: pln.
sort_dirNoSort direction (default: desc).
has_emailNotrue = only companies with email on record. Matching rows include contacts.email. Omit otherwise.
is_activeNotrue = active only, false = closed only. Omit for all.
ebitda_maxNoMaximum EBITDA.
ebitda_minNoMinimum EBITDA.
legal_formNoLegal form fragment, e.g. 'spółka z o.o.' or 'akcyjna'.
profit_maxNoMaximum net profit.
profit_minNoMinimum net profit.
capital_maxNoMaximum share capital.
capital_minNoMinimum share capital.
has_websiteNotrue = only companies with website on record. Matching rows include contacts.website. Omit otherwise.
postal_codeNoPostal code prefix, e.g. '00-9' or '61-'.
revenue_maxNoMaximum total revenue.
revenue_minNoMinimum total revenue.
family_businessNotrue = family business (people with the same surname hold ≥50%).
total_assets_maxNoMaximum total assets.
total_assets_minNoMinimum total assets.
estimated_value_maxNoMaximum Ohlson estimated equity value in PLN.
estimated_value_minNoMinimum Ohlson estimated equity value in PLN.
ownership_structureNoOwnership: pl_independent = Polish company controlled by individuals; pl_group = part of a Polish group (a Polish company holds ≥50%); foreign_group = foreign shareholders ≥50% or foreign parent (GLEIF / CRBR).
profit_operating_maxNoMaximum operating profit (PLN). Omit if unused.
profit_operating_minNoMinimum operating profit (PLN). Negative allowed. Omit if unused.
registration_date_maxNoLatest KRS registration date, YYYY-MM-DD (inclusive).
registration_date_minNoEarliest KRS registration date, YYYY-MM-DD (inclusive). For newly registered companies use today's date for both registration_date_min and registration_date_max.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / service
      Added value: +{
      +  "description": "Service the company offers (Compabase services dictionary, from company websites): service name in Polish/English/German, e.g. 'księgowość', 'heat pumps', or slugs from compabase.com/services, comma-separated (any of them).",
      +  "type": "string"
      +}
  2. Changed4 schema fields changed
    • addedInput schema / properties / family_business
      Added value: +{
      +  "description": "true = family business (people with the same surname hold ≥50%).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / naics
      Added value: +{
      +  "description": "Detailed industry: NAICS 6-digit codes, comma-separated (any of them), e.g. '541511,541512'. AI classification of what the company actually does.",
      +  "type": "string"
      +}
    • addedInput schema / properties / niche
      Added value: +{
      +  "description": "Detailed industry in words (Polish), matched against the company's niche, e.g. 'opakowania', 'software house', 'catering'.",
      +  "type": "string"
      +}
    • addedInput schema / properties / ownership_structure
      Added value: +{
      +  "description": "Ownership: pl_independent = Polish company controlled by individuals; pl_group = part of a Polish group (a Polish company holds ≥50%); foreign_group = foreign shareholders ≥50% or foreign parent (GLEIF / CRBR).",
      +  "enum": [
      +    "pl_independent",
      +    "pl_group",
      +    "foreign_group"
      +  ],
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • changedInput schema / properties / sort_by / description
      Previous value: -"Sort field (default: revenue_total). registration_date + sort_dir=desc lists the newest registrations first."New value: +"Sort field (default: revenue_total). registration_date + sort_dir=desc lists the newest registrations first. revenue_growth_pct + sort_dir=desc lists the fastest-growing companies (y/y revenue growth from KRS financial statements; combine with revenue_min to skip small companies)."
    • changedInput schema / properties / sort_by / enum
      Previous value: -[
      -  "revenue_total",
      -  "profit_net",
      -  "total_assets",
      -  "profit_operating",
      -  "ebitda",
      -  "capital_total",
      -  "estimated_value",
      -  "registration_date"
      -]New value: +[
      +  "revenue_total",
      +  "profit_net",
      +  "total_assets",
      +  "profit_operating",
      +  "ebitda",
      +  "capital_total",
      +  "estimated_value",
      +  "registration_date",
      +  "revenue_growth_pct"
      +]
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare a safe read (readOnly, idempotent, non-destructive, closed-world); the description adds substantive behavior beyond that — RODO gating hides JDG companies without a public email, sparse PKD results carry a `hint` field, and fields=full 'may exceed client size limits'. That is exactly the operational context an agent needs to interpret empty or truncated results.

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 resource and its exclusions, and every sentence carries information — nothing is filler. It is a dense run-on paragraph with heavy backtick use, though, and would scan better split into scope / response modes / usage blocks.

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 40-parameter filter tool with no output schema, the description covers the gaps that matter: what each fields mode returns, default result size, the RODO-driven sparsity caveat, and the hint field. An agent has enough to call it correctly and interpret a thin result set.

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, but the description adds real guidance beyond the schema: the default `fields=summary` payload contents, the size tradeoff for `fields=full`, and the interaction rule to combine revenue_growth_pct sorting with revenue_min to skip small companies. It does not, however, cover the many financial min/max pairs, which rely entirely on the schema.

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?

Specific verb+resource: 'Search and filter Polish KRS companies (spółki)', and it immediately carves out scope by naming what it does not cover (the CEIDG/JDG register) and which sibling handles bulk output (export_companies). An agent can distinguish this from get_company or export_companies without opening a 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?

Explicit when-to-use list: 'rankings, sector filters, city/county/region browsing, name search, or NIP/KRS lookup', plus a negative rule ('omit year when looking up a company by name, KRS, or NIP'). It also routes the agent between its own response modes and a sibling: 'For a handful of emails or phones, fields=contacts_only here is enough; export_companies is meant for bulk files.'

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.