entyrix-mcp
MCP server for the Entyrix European business-registry (KYB) API, exposing 10 stdio tools for searching, looking up, and analyzing companies across multiple jurisdictions. Enables LLM clients to perform company registry searches, financial lookups, compliance checks, and more.
README
@entyrix/mcp
Model Context Protocol (MCP) server for the Entyrix European business-registry (KYB) API. Exposes 10 stdio tools so LLM clients (Claude Desktop, Claude Code, Cursor, ChatGPT) can search, look up, and analyze companies across SK, CZ, AT, EE, SI, LV, UK and more (16+ jurisdictions, growing).
30-second quickstart
npm install -g @entyrix/mcp
export ENTYRIX_API_KEY=your-api-key-here
entyrix-mcp
Or run without installing:
export ENTYRIX_API_KEY=your-api-key-here
npx @entyrix/mcp
Get an API key at https://entyrix.com.
Tools
| Tool | Description |
|---|---|
search_companies |
Fuzzy/typo-tolerant name search (server-side 26-62 ms cold, ~1 ms cached; measured 2026-08-11) |
lookup_company |
Resolve a company by national registry ID, country-aware (SK/CZ/AT/EE/SI/LV/…) |
get_company_details |
Full profile: financials, tech stack, security, NIS2, sanctions, credit grade |
get_company_network |
Shared-officer graph — related entities via common directors/officers |
get_company_relations |
Directors, UBO / beneficial owners, M&A and succession links |
advanced_search |
57-key filter search (country, NACE, turnover, credit grade, NIS2, sanctions, tech, …) |
check_compliance |
AML / sanctions / debtor lists / RPVS check (SK) |
get_financials |
Last N years of turnover, profit, EBITDA, ROA, ROE |
find_suppliers |
Public-sector contracts where company is supplier (SK CRZ) |
list_rankings |
Pre-computed leaderboards (top turnover, top employers, …) |
Configuration
| Env var | Default | Description |
|---|---|---|
ENTYRIX_API_KEY |
(required) | Bearer token from your Entyrix dashboard |
ENTYRIX_BASE_URL |
https://entyrix.com |
Override for staging / self-hosted |
ENTYRIX_TIMEOUT_MS |
30000 |
HTTP timeout per request |
Client setup
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"entyrix": {
"command": "npx",
"args": ["-y", "@entyrix/mcp"],
"env": {
"ENTYRIX_API_KEY": "your-api-key-here"
}
}
}
}
Restart Claude Desktop. The 10 tools appear in the tools panel.
Claude Code
Register the server from any project (writes to ~/.claude.json):
claude mcp add entyrix --env ENTYRIX_API_KEY=your-api-key-here -- npx -y @entyrix/mcp
Or add it manually to .mcp.json in your project root (checked in) / ~/.claude.json (global):
{
"mcpServers": {
"entyrix": {
"command": "npx",
"args": ["-y", "@entyrix/mcp"],
"env": {
"ENTYRIX_API_KEY": "your-api-key-here"
}
}
}
}
Cursor
Edit .cursor/mcp.json in your workspace (or ~/.cursor/mcp.json for global):
{
"mcpServers": {
"entyrix": {
"command": "npx",
"args": ["-y", "@entyrix/mcp"],
"env": {
"ENTYRIX_API_KEY": "your-api-key-here"
}
}
}
}
ChatGPT
ChatGPT does not consume MCP stdio servers directly today. Two integration paths:
1. Custom GPT Actions — expose Entyrix endpoints as OpenAPI actions. Sketch:
openapi: 3.1.0
info:
title: Entyrix
version: 0.1.0
servers:
- url: https://entyrix.com/api/v1
paths:
/companies/autocomplete:
get:
operationId: searchCompanies
parameters:
- name: q
in: query
required: true
schema: { type: string }
- name: country
in: query
schema: { type: string, minLength: 2, maxLength: 2 }
responses:
"200": { description: OK }
/companies/{country}/{national_id}:
get:
operationId: lookupCompany
parameters:
- { name: country, in: path, required: true, schema: { type: string } }
- { name: national_id, in: path, required: true, schema: { type: string } }
responses:
"200": { description: OK }
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
security:
- BearerAuth: []
Paste this into the Custom GPT builder, set the auth header, and the Entyrix endpoints become first-class GPT actions.
2. Connectors API (enterprise) — <https://platform.openai.com/docs/connectors> accepts MCP servers behind an HTTP wrapper; a small HTTP-to-stdio adapter is on the roadmap.
Development
git clone <repo>
cd entyrix-mcp
npm install
npm run build
npm test
Local stdio sanity-check (requires a real API key):
ENTYRIX_API_KEY=your-key node dist/index.js
# (stdin/stdout speaks MCP — wire it to a client to actually issue calls)
Quality gates
Every PR must pass:
npm run format
npm run lint
npx tsc --noEmit
npm test
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.