Skip to main content
Glama

Company registry card

company_snapshot
Read-onlyIdempotent

Get a company registry card, as in REST API GET /v1/companies/{slug}.

Use it for officers (current roles from published acts), sole_shareholder as printed, capital_eur, address, status, NIF with its source, public_contracts and a size_hint estimate. For dated acts use company_history. Names are searched as in company_history: multiple matches return {ambiguous: true, candidates, candidate_names with name, province and status}; no match returns {error, suggested_companies}.

Returns company_slug, current_name, nif, nif_caveat, sources and other card fields; former_slugs for a merged company. lei: GLEIF Legal Entity Identifier matched by NIF; null means no match yet. website: from the newest BORME act about the company website; null if none or removed. BORME does not report minority shareholdings, employee counts or revenue.

Read-only; one request per call. Requires basic plan or higher; send your API key in X-API-Key (https://bormeapi.com/account).

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": {
      "company": "<company>"
    },
    "name": "company_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyYesCompany slug, e.g. vaz-metales-sl (from search_companies), or a name of at least 3 letters or digits, e.g. "Mercadona", searched case-insensitively as in company_history.
include_inferredNoOptional, default false, e.g. true. true allows an inferred sector when the snapshot has no CNAE code: the newest eligible decision among the company's latest 500 events without a printed code fills `cnae` with a CNAE-2009 division, `cnae_version` `2009`, `cnae_source` `jev` and `cnae_inference` (`confidence`, `model`, `prompt`, `section`, `note`, `event_id`, `date`); with none eligible, none is added. It is the output of a language model (TypeSafe Jev, model `typesafe-ai/jev-1.14.0`, prompt ID `two-stage-v1`), not a code published in BORME, and it describes the objeto social, not the company's verified activity. Only decisions whose confidence meets the threshold are returned (default 0.9). Inferred values are included only on request: if you omit `include_inferred` or set it to `false`, there are none. Only acts published from 2024-11-05 have inferred divisions (`note`), so more sector coverage from that date may reflect them and does not, by itself, show market growth.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, it discloses access requirements (basic plan or higher, X-API-Key header), the one-request-per-call cost, and the exact shapes of the ambiguous-match and error responses. It also sets honest expectations by stating BORME does not report minority shareholdings, employee counts or revenue, and explains null semantics for lei and website.

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?

Purpose and the sibling pointer are front-loaded, and the field list is compact. A few clauses are dense or near-redundant (repeated notes about name searching and null handling), but every section carries useful information for calling the tool correctly.

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?

With no output schema, the description carries the return-value burden and does so: it names the returned fields, the merged-company former_slugs case, and the null cases for lei and website. Combined with auth, plan tier and error/ambiguity handling, nothing an agent needs before calling is missing.

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% and the schema already documents both parameters in depth, so the description does not need to restate them. It still adds value by describing what happens when the company string matches multiple names (ambiguous result with candidates) versus none (error with suggested_companies), which is behavior the schema does not convey.

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 and resource ("Get a company registry card"), anchors it to the concrete REST endpoint GET /v1/companies/{slug}, and enumerates the card fields it returns. It also explicitly contrasts itself with company_history for dated acts, so an agent can separate the two 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 Guidelines4/5

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

The description names the alternative for historical acts ("For dated acts use company_history") and explains that name lookups behave the same way as in that sibling, giving clear routing context. It does not spell out when-not-to-use for the other obvious alternatives (company_by_nif, search_companies), but the primary fork is stated.

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.