mcpField
L
Latvia Beneficial Owners

Latvia Beneficial Owners

Remote
pipeworx.ioLegal & Government0Updated 1w ago

About Latvia Beneficial Owners

This MCP server retrieves beneficial-owner records from Latvia’s open register by company registration number. It is for users checking entity ownership; results include owner details and registration dates, with a mechanism for withholding names on request.

Key features

  1. 01Look up owners by registration number
  2. 02Return names, birth dates, and nationality
  3. 03Include country of residence and filing date
  4. 04Report missing records and withheld-name counts

Use cases

  1. 01Check beneficial owners of Latvian entities
  2. 02Research company ownership and register filings

MCP support

Exposes a registration-number lookup tool to MCP clients through the Pipeworx gateway or as a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/latvia-beneficial-owners/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

@pipeworx/latvia-beneficial-owners

A Latvian legal entity's beneficial owners -- forename, surname, date of birth, nationality, country of residence and registration date -- from Latvia's beneficial-owners open data, published by LR Uznemumu registrs (Latvia Enterprise Register).

Part of Pipeworx — an MCP gateway connecting AI agents to 1847+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Fleet #3332, Bruce's build-names ruling (#3329, CLAUDE.md "What we will source" -> personal data). Loaded live 2026-10-19 (Bruce, direct): 199,964 lv_beneficial_owners rows across 164,174 entities, verified table-count-matched against the ingest manifest.

Tools

  • lv_beneficial_owners(registration_number) -- every beneficial owner on file for one Latvian legal entity, by its unique registration number (e.g. "40008018725"). Returns each owner's forename+surname, date of birth, the register's own partially-masked personal code, nationality and country of residence (ISO-2 codes -- never a street address), and the date the holding was registered. A registration number with no rows answers found: false, reason: "not_held", not a bare [] -- a company can genuinely have no beneficial-owner entry on file.

Auth

Keyless. The tool answers only through the Pipeworx gateway, which holds the D1 mirror; a standalone npm install has no data to read, and the tool throws a clear "not bound in this runtime" error there instead of returning an empty list.

Personal data

Beneficial owners' names, dates of birth, and nationality/residence (country-level only) are served under Bruce's build-names ruling (fleet #3329/#3332). A shared removal mechanism (@pipeworx/shared's applyRemovals, the same one sos-entities uses under the 2026-10-08 names-and-roles ruling) withholds any name on request to [email protected] -- withheld_by_removal_request on every response says how many were suppressed for that lookup. No address of any kind (the residence field is a country code, confirmed against a live sample of the open-data file -- never a street address) is collected or served.

Data sources

  • LR Uznemumu registrs (Latvia Enterprise Register), beneficial owners open data. Licence: CC0-1.0 (public domain dedication), published on Latvia's national open-data portal. Refreshed by the publisher on its own schedule (observed daily); this pack refreshes on the same cadence once the daily workflow is applied (currently a proposal -- proposals/agent-config/.github/workflows/latvia-beneficial-owners-refresh.yml -- CLAUDE.md's agent-config-paths push ruleset blocks a direct .github/workflows/ edit, so a human applies it). The exact download route lives only in scripts/latvia-beneficial-owners/refresh.sh (CLAUDE.md step 9b).

Refreshing the mirror

bash scripts/latvia-beneficial-owners/refresh.sh build   # download + build local SQLite; no remote writes
bash scripts/latvia-beneficial-owners/refresh.sh load    # the above, then replace the D1 tables and verify

Automated daily once the proposed workflow above is applied; until then, run by hand or via gh workflow run after it lands.

Schema

scripts/latvia-beneficial-owners/schema.sql: lv_beneficial_owners (one row per owner-entity pair) + lv_meta (key/value: data_as_of, source, licence). Must stay in sync with src/store.ts's BeneficialOwnerRow.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "latvia-beneficial-owners": {
      "url": "https://gateway.pipeworx.io/latvia-beneficial-owners/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/latvia-beneficial-owners/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1847+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/lv_beneficial_owners \
  -H 'Content-Type: application/json' \
  -d '{"registration_number":"40008018725"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/lv_beneficial_owners. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "latvia-beneficial-owners": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-latvia-beneficial-owners"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-latvia-beneficial-owners

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Latvia Beneficial Owners data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.