Skip to main content
Glama

Find Swiss companies by name, purpose, canton, legal form, industry, location and lead score

search_companies
Read-onlyIdempotent

Search Swiss companies of every legal form: name, canton, legal form, industry, location, registration date, capital, discovered contact details, and the analysis block (lead/viability score, mailbox-company and dissolution flags, size, confidence tier, buyer profiles, growth signals). Nothing is silently ignored — an unknown closed-set value or a free-text term under 3 characters is rejected — so an empty page is a real zero for this dataset, which holds every company still in the register and a deleted one only if a SHAB publication named it since the dataset began; for anything else try find_company_by_name against the live register. Every analysis filter matches only analysed companies, so an empty page there means none analysed matched; analysisStatuses says how much was in scope. purpose is the exception and the way to ask what a company does: it searches the register's own purpose clause, which every company has, and the English AI summary together, so an unanalysed company is still found by its own words, and with no sort the most relevant come first. Unscored companies sort last, so pair a score sort with its minimum. Rows carry the filterable fields only — get_companies for the purpose, address, contact data and full analysis block.

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
cityNoCity / town name (partial match, min 3 chars)
sizeNoPage size, max 100 (default 20)
sortNoOrdering: REGISTRATION_DATE_DESC (default, or relevance when a purpose term is given), REGISTRATION_DATE_ASC, LEAD_SCORE_DESC, VIABILITY_SCORE_DESC. Companies with no score sort last, so a score ordering is not a substitute for the matching minimum filter.
cursorNonextCursor from the previous page; omit to start at the beginning. Opaque — pass it back verbatim, and keep the same filters and sort or it is rejected.
searchNoFree-text match on UID, CH-ID, or the firm name of legal entities (min 3 chars; shorter is rejected). Sole-proprietor/partnership names are not name-searchable.
streetNoStreet name (partial match, min 3 chars)
cantonsNoTwo-letter canton codes, e.g. ["ZH","BE"]; anything else is rejected
purposeNoWhat the company does (min 3 chars per term). Terms are alternatives; words inside one term must all appear. Nothing is translated: the purpose clause is written in German, French or Italian, and one language finds only the companies that filed in it, so pass all three wordings — ["Photovoltaik","photovoltaique","fotovoltaico"]. An English term reaches the AI summary instead, so on its own it finds analysed companies only. Words match as prefixes and accents are ignored.
zipCodeNoPostal code (prefix match), e.g. "80" or "8001"
hasEmailNotrue keeps only companies with a discovered email
industryNoAI industry or sub-industry (partial match, min 3 chars), e.g. "software"
statusesNoStatuses: ACTIVE, CANCELLED, BEING_CANCELLED. A company held by its register entry alone (no lastPublicationDate) has no status yet and matches none of them
capitalMaxNoMaximum nominal capital, in the company's own currency
capitalMinNoMinimum nominal capital, in the company's own currency
hasContactNotrue keeps only companies with a discovered email or website
hasWebsiteNotrue keeps only companies with a discovered website
legalFormsNoLegal forms, by abbreviation or full name in any official language, e.g. ["AG","GmbH"], ["SA","Sàrl"] or ["Genossenschaft"]; an unknown one is rejected. Catalog: vetari://allowed-values/legalForm
isDissolvedNotrue keeps only companies the AI marks dissolved, false only those it marks not dissolved; no verdict matches neither
likelyNeedsNoAI likely needs the company may have, e.g. ["BOOKKEEPING","CORPORATE_LAW"]; one of BOOKKEEPING, STATUTORY_AUDIT, TAX_ADVISORY, PAYROLL_SERVICES, CORPORATE_LAW, EMPLOYMENT_LAW, IP_TRADEMARK, CONTRACT_LAW, REGULATORY_COMPLIANCE, RECRUITING, HR_OUTSOURCING, BUSINESS_BANKING, CORPORATE_FINANCE, BUSINESS_INSURANCE, PENSION_BENEFITS, IT_INFRASTRUCTURE, SOFTWARE_DEVELOPMENT, CYBERSECURITY, DIGITAL_MARKETING, WEB_ECOMMERCE, OFFICE_SPACE, FACILITY_MANAGEMENT, LOGISTICS_WAREHOUSING, PROCUREMENT, INDUSTRY_SPECIFIC
companySizesNoAI size buckets: SOLO, MICRO, SMALL, MEDIUM, LARGE, UNKNOWN
maxLeadScoreNoMaximum lead score, 1-10
minLeadScoreNoMinimum lead score, 1-10 (10 = hottest lead) — a different scale from the viability score
registeredToNoRegistered on/before this ISO date (YYYY-MM-DD)
growthSignalsNoAI growth signals: SUBSTANTIAL_CAPITAL, SOLID_CAPITALIZATION, MULTI_PERSON_TEAM, INTERNATIONAL_TEAM, TECHNOLOGY_ORIENTED, DIVERSIFIED_OFFERING, CONDITIONAL_CAPITAL_PROVISION, CAPITAL_BAND_FLEXIBILITY, IN_KIND_CONTRIBUTION, DETAILED_PURPOSE
registeredFromNoRegistered on/after this ISO date (YYYY-MM-DD)
capitalCurrencyNoCapital currency, e.g. "CHF" — capital bounds do not convert between currencies, so pair them with this
confidenceTiersNoAI confidence in its own analysis: HIGH, MEDIUM, LOW
analysisStatusesNoAnalysis states: NOT_ANALYSED, INCOMPLETE, ANALYSED
isMailboxCompanyNotrue keeps only companies whose registered purpose states no operating activity and whose setup corroborates it, false only those with an operating purpose; a company with no verdict matches neither
maxViabilityScoreNoMaximum viability score, 0-100
minViabilityScoreNoMinimum viability score, 0-100 — a different scale from the lead score
targetBuyerProfilesNoWho the AI thinks would sell to this company: B2B_SOFTWARE_VENDOR, PROFESSIONAL_SERVICES_FIRM, FINANCIAL_ADVISOR, REAL_ESTATE_AGENT, HR_RECRUITER, MARKETING_AGENCY, LOGISTICS_PROVIDER, INDUSTRY_SUPPLIER

Output Schema

NameRequiredDescriptionDefault
dataYes
sourceYes
disclaimerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / statuses / description
      Previous value: -"Statuses: ACTIVE, CANCELLED, BEING_CANCELLED"New value: +"Statuses: ACTIVE, CANCELLED, BEING_CANCELLED. A company held by its register entry alone (no lastPublicationDate) has no status yet and matches none of them"
  2. Changed1 schema field changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
  3. Changed2 schema fields changed
    • addedOutput schema / properties / data / properties / page / properties / totalCapped
      Added value: +{
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / data / properties / page / required
      Previous value: -[
      -  "size",
      -  "totalElements"
      -]New value: +[
      +  "size"
      +]
  4. Changed4 schema fields changed
    • changedInput schema / properties / maxLeadScore / description
      Previous value: -"Maximum AI lead score, 1-10"New value: +"Maximum lead score, 1-10"
    • changedInput schema / properties / maxViabilityScore / description
      Previous value: -"Maximum AI viability score, 0-100"New value: +"Maximum viability score, 0-100"
    • changedInput schema / properties / minLeadScore / description
      Previous value: -"Minimum AI lead score, 1-10 (10 = hottest lead) — a different scale from the viability score"New value: +"Minimum lead score, 1-10 (10 = hottest lead) — a different scale from the viability score"
    • changedInput schema / properties / minViabilityScore / description
      Previous value: -"Minimum AI viability score, 0-100 — a different scale from the lead score"New value: +"Minimum viability score, 0-100 — a different scale from the lead score"
  5. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety and determinism are covered. The description adds genuinely non-obvious behavior beyond that: nothing is silently ignored, empty pages are true zeros for this dataset, analysis filters match only analysed companies, and unscored companies sort last. Strong additions, but the dataset/result semantics are the focus rather than the read-only contract already in annotations.

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 empty-page guarantee and the purpose/analysis-filter distinction are correctly front-loaded, and most sentences carry real information. However, it is a single dense paragraph of long compound sentences, and several clauses (three-language purpose wording, sort ordering) duplicate schema descriptions, so it is heavier than needed for a tool whose parameters are already fully documented.

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 32-parameter tool with an output schema, the description covers the things structured fields cannot: what an empty result means, which filters require prior analysis, how the dataset's coverage is bounded, and that rows omit purpose/address/contact detail. Nothing an agent needs in order to interpret a result correctly is missing.

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 coverage is 100% and the per-parameter descriptions already carry the language, currency and score-scale caveats, so the baseline is 3. The prose adds cross-parameter meaning (pair a score sort with its minimum, capital bounds do not convert) but largely restates what the schema fields already say.

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?

Opens with a specific verb+resource ("Search Swiss companies of every legal form") and enumerates the filterable dimensions, then explicitly contrasts with find_company_by_name (live register) and get_companies (purpose, address, contact, full analysis block). An agent can distinguish this from every named sibling 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?

Gives explicit routing: use find_company_by_name for companies not in this dataset, and get_companies when full detail is needed rather than filterable fields. It also states the when-to-use rule for purpose search versus analysis filters, plus the sort/minimum-score pairing requirement, so exclusions and alternatives are named rather than inferred.

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.

Resources