mcpField
B
Bulgaria Beneficial Owners

Bulgaria Beneficial Owners

Remote
pipeworx.ioLegal & Government0Updated 5d ago

About Bulgaria Beneficial Owners

This MCP server looks up beneficial owners in Bulgaria’s commercial and nonprofit legal-entity registers by EIK/UIC. It reads the register for each request and includes context when no natural-person owner is on file, for legal and business research use.

Key features

  1. 01Look up owners by EIK/UIC
  2. 02Return nationality and stated residence country
  3. 03Include the register’s control description
  4. 04Explain records with no natural-person owner
  5. 05Support name suppression on request

Use cases

  1. 01Check beneficial owners of Bulgarian entities
  2. 02Review registered descriptions of control
  3. 03Understand why no natural-person owner is listed

MCP support

It exposes the `bg_beneficial_owners` tool to MCP clients through the Pipeworx gateway or a local stdio MCP server. Gateway connections also include shared meta-tools.

Configuration

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

Endpointhttps://gateway.pipeworx.io/bulgaria-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/bulgaria-beneficial-owners

A Bulgarian legal entity's beneficial owners (действителни собственици), from the Registry Agency's (Agentsia po vpisvaniyata) Commercial Register and Register of Non-Profit Legal Entities. Fleet #3332, Bruce's build-names ruling on #3329.

Part of Pipeworx — an MCP gateway connecting AI agents to 1875+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

  • bg_beneficial_owners(eik) — a Bulgarian legal entity's beneficial owners by its EIK/UIC (the 9-digit unified identification code; 13 digits for a foreign-company branch). Returns each owner's name, the country the register names for them, country of residence when the register states one, and the register's OWN free-text description of their manner of control. Some entries are the AMLD fallback category — a senior managing official recorded when no other beneficial owner can be established — rather than a true economic owner, and manner_of_control says which, in the register's own words. An entity whose record carries no natural-person owner on file (common when the ownership chain resolves only through other companies) answers found: true with an empty owner list and register_note explaining why, never a silent empty array with no context.

Read live, per request — the Registry Agency publishes no bulk open-data extract of this field, so data_as_of is the day of the call, not a mirror refresh date.

Auth

Keyless. No account, login or payment is needed to read this field — the register's own public search tool serves it the same way.

Personal data

Beneficial owners' names and country-level nationality/residence (never a street address) are served under Bruce's build-names ruling (fleet #3329/#3332, verified live and free of login 2026-10-18/19). 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.

Data sources

  • Registry Agency (Agentsia po vpisvaniyata), Commercial Register and Register of Non-Profit Legal Entities — the statutory register every Bulgarian legal entity's beneficial-ownership declaration is filed into under Bulgaria's anti-money-laundering law. The exact route lives only in src/index.ts (CLAUDE.md step 9b).

A note on verification

This pack's live fetch was verified with curl (200, real data, no account). A plain Node fetch() call to the same endpoint from this development machine returned HTTP 500 with an empty body on several attempts, while curl against the identical URL succeeded every time — consistent with a WAF/CDN fingerprinting the TLS client rather than an auth or rate-limit wall (no 401/403, no login redirect, just a bare 500). The Cloudflare Workers runtime this pack actually runs under is neither curl nor Node, so this is unresolved until the post-deploy live probe confirms which side of that line it falls on. If it turns out blocked from Workers too, the answer is the same as for any WAF block: document it, do not try to defeat it.

Quick Start

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

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

tools/list at https://gateway.pipeworx.io/bulgaria-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 1875+ 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/bg_beneficial_owners \
  -H 'Content-Type: application/json' \
  -d '{"eik":"130007884"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/bg_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": {
    "bulgaria-beneficial-owners": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-bulgaria-beneficial-owners"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-bulgaria-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 Bulgaria 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.