Skip to main content
Glama

Gleif Find By Registration Number

gleif_find_by_registration_number
Read-onlyIdempotent

Reverse lookup: which company holds this state or national register number? Give a company registration number (a Delaware file number, a British company number, a French SIREN, a Norwegian organisation number and so on) and get back the LEI records in GLEIF that carry it, each with its LEI, legal name, status, jurisdiction, registered address, the register that issued the number (id and name) and the number itself. Optionally narrow by registration_authority (GLEIF register id such as RA000602 for the Delaware Division of Corporations) or jurisdiction (US-DE, GB, DE). A number can exist in more than one register, so several hits come back as several labelled rows, never one guess; narrow with registration_authority or jurisdiction to pick one. Numbers are matched as published after removing invisible direction marks and surrounding spaces; leading zeros are never added or removed (00041424 and 41424 are different numbers), and some registers publish ids with internal spaces (the Norwegian register, "923 609 016"), so pass those with their spaces. Zero hits does NOT mean no such company: GLEIF only holds entities that obtained an LEI, so check company_register_search (company registers across countries) or sos_search (US state registers).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "jurisdiction": "US-DE",
      "registration_number": "10084845"
    },
    "name": "gleif_find_by_registration_number"
  }
}

Input Schema

NameRequiredDescriptionDefault
page_sizeNo1-100 matching records to return (default 25).
jurisdictionNoOptional jurisdiction of the entity: ISO 3166-1 alpha-2 country ("GB") or ISO 3166-2 region ("US-DE").
registration_numberYesThe company's own register number, e.g. "10084845" (Delaware file number) or "00041424" (United Kingdom).
registration_authorityNoOptional GLEIF registration authority id of the register that issued the number, "RA" + 6 digits, e.g. "RA000602" (Delaware), "RA000585" (United Kingdom). Bare digits are accepted.

Output Schema

NameRequiredDescriptionDefault
noteYesCoverage caveat: a miss means no LEI under this number, not that no such company exists
sourceYesPublisher and dataset
recordsYesMatching LEI records; one row per LEI, labelled with its register
returnedNoRecords in this response
total_matchesYesRecords whose register number equals the asked number
truncated_upstreamNoTrue when GLEIF held more candidate rows than were read
jurisdiction_filterNoJurisdiction filter applied, or null
registration_number_askedYesThe number as received, after removing invisible marks and surrounding spaces
registration_authority_filterNoRegister id filter applied, or null
registration_number_canonicalNoThe number with all whitespace removed, used to compare against records

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, open-world and non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: multiple registers can hold the same number and hits are returned as labelled rows rather than one guess, and zero hits does not mean the company lacks a register entry because GLEIF only contains LEI holders. The matching-normalization rules (direction marks and surrounding spaces stripped, leading zeros preserved, internal spaces significant) are strong value-add; only the absence of any note on result ordering/pagination handling beyond page_size keeps it from a 5.

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?

The core question is front-loaded and the paragraph then moves logically through output, narrowing, matching rules, and zero-hit fallback. It is dense but nearly every clause carries information an agent would otherwise get wrong; a few parentheticals (the Delaware/Norwegian examples repeated in the schema) are redundant and a sentence break or two would aid scanning.

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?

The tool ships an output schema, yet the description still summarizes the returned fields (LEI, legal name, status, jurisdiction, address, issuing register) and, more importantly, covers the failure mode and disambiguation strategy unique to this lookup. Nothing needed to invoke it correctly — required number, optional narrowing, normalization rules, fallback — 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%, so the baseline is 3; the description rises above it by explaining matching semantics the schema cannot express — that '00041424 and 41424 are different numbers' and that register ids with internal spaces must be passed with spaces. It also glosses registration_authority as a GLEIF register id and jurisdiction as ISO region or country, but those duplicate the schema's own examples.

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 framing — 'Reverse lookup: which company holds this state or national register number?' — naming both the verb (lookup) and the resource (register number → LEI records), and immediately contrasts with the forward LEI lookup implied by the get_lei sibling. The parenthetical examples (Delaware file number, British company number, SIREN, Norwegian organisation number) pin down the input domain unambiguously.

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?

States explicit narrowing conditions ('Optionally narrow by registration_authority ... or jurisdiction') and explains why several rows can come back and how to reduce to one. It also names concrete fallbacks for zero hits — 'check company_register_search ... or sos_search' — which is exactly the when-not-to-use guidance an agent needs.

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.