Skip to main content
Glama

BORME API - Spain company registry

by com.bormeapi.mcp
OverviewDiscussionsAdmin

search_companies

Find Spanish companies by name and return ranked company cards (slug, status, province). Use it first when the user gives a company name, then company_history with the slug.

Matches current names, former names and name variants, ignoring accents, case, punctuation and the legal form. Each card's match is exact, prefix, contains or fuzzy (only when nothing else matched: a lead, not an identification; say so); matched_on says which name matched. Ranked by match, then active companies first, then the newest act.

Plans: the free plan's events cover 7 days, but this search is not limited by history. Without a key a search shows 5 cards and hidden_by_plan counts the rest (matches_beyond_limit, a lower bound when matches_is_at_least): relay its note. The NIF is on the card from the basic plan up: send your key in the X-API-Key header. An empty answer is not proof that a business does not exist; relay the response's note in the user's language.

Input Schema

NameRequiredDescriptionDefault
nameYesCompany name or part of it, at least 3 letters or digits; accents, case, punctuation and legal form are ignored.
limitNoCards per page, 1-50 (default 10).
offsetNoCards to skip. At most 200 cards are ranked; truncated true means more candidates existed, so add another word from the name.
statusNoOne of active, dissolved, extinct, sheet_closed; applied like province.
provinceNoThe company's province, accent-insensitive, e.g. MADRID, VIZCAYA, or an autonomous community for all of its provinces, e.g. Catalonia; several values can be separated by commas, e.g. BIZKAIA,GIPUZKOA. Applied to the candidates the search reads (2,000 with a filter), so a broad name can return fewer companies than match it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / province / description
      Previous value: -"The company's province, accent-insensitive, e.g. MADRID, VIZCAYA. Applied to the candidates the search reads (2,000 with a filter), so a broad name can return fewer companies than match it."New value: +"The company's province, accent-insensitive, e.g. MADRID, VIZCAYA, or an autonomous community for all of its provinces, e.g. Catalonia; several values can be separated by commas, e.g. BIZKAIA,GIPUZKOA. Applied to the candidates the search reads (2,000 with a filter), so a broad name can return fewer companies than match it."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

No annotations exist, so the description carries the full burden and does: it discloses normalization rules (accents, case, punctuation, legal form ignored), ranking order (match type, then active first, then newest act), and plan-gating behavior (5 cards unauthenticated, `hidden_by_plan`, `matches_is_at_least` as a lower bound). It also states the auth requirement (X-API-Key header) and that NIF appears only from the basic plan up, which is exactly the kind of beyond-schema behavior an agent needs.

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 next-call instruction are front-loaded, and each paragraph covers a distinct concern (matching, ranking, plans, caveats). It is longer than average and repeats the instruction to relay the response `note` twice ('relay its note' and 'relay the response's `note` in the user's language'), a small redundancy in otherwise dense prose.

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 annotations and no output schema, the description supplies everything the agent needs: the card fields, the meaning of `match` and `matched_on`, the plan-dependent fields (`hidden_by_plan`, `matches_beyond_limit`), and the failure-mode guidance. Nothing material about invoking or interpreting the call is left unstated.

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; the description earns above that by explaining how plan limits interact with `limit`/`offset` and how status/province filtering is applied to the 2,000-candidate window, which the schema only hints at. It does not restate the numeric bounds, correctly leaving those to 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?

Opens with a specific verb and resource ('Find Spanish companies by name') and immediately states the return shape ('ranked company cards (slug, status, province)'). It also distinguishes itself from the sibling company_history by prescribing the ordering of calls, so an agent can tell the two apart without inspecting 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?

Explicitly says 'Use it first when the user gives a company name, then company_history with the slug', naming the alternative and the sequencing condition. It further bounds interpretation of results (fuzzy matches are 'a lead, not an identification; say so') and warns that an empty answer is not proof of non-existence.

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

All BORME API - Spain company registry toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources