Skip to main content
Glama

Leadgen — Romanian ONRC Business Registry (API + MCP)

Free, read-only access to Romania's official business registry (ONRC): every registered company, its CAEN activities, legal representatives, status, and 2025 financial statements — built from the state's own open-data dump and exposed over a tiny HTTP API and an MCP server.

  • 4,196,860 companies

  • 19.3M CAEN activity records

  • 3.68M legal representatives

  • 4.64M status entries

  • 2025 financial statements loaded

Live endpoints (free, no auth)

REST APIhttps://onrc-api.adrianhomelab.com

Endpoint

Description

GET /lookup_business?query=<name|CUI>&max_results=N

Search companies by name or tax code (CUI).

GET /lookup_director?name=<name>&max_results=N

Find companies by director / legal-representative name.

GET /docs

Interactive OpenAPI docs (Swagger UI).

GET /health

Liveness check.

The landing page at https://onrc-api.adrianhomelab.com/ documents the schema with a worked example.

MCP serverhttps://hermes.adrianhomelab.com/mcp (Streamable HTTP). Point any MCP client at that URL. Tools: lookup_business, lookup_director, lookup_financials, extract_contacts, lookup_domain.

Related MCP server: ENTIA Entity Verification

Try it

# search by company name
curl "https://onrc-api.adrianhomelab.com/lookup_business?query=DEDEMAN&max_results=3"

# search by CUI (tax code)
curl "https://onrc-api.adrianhomelab.com/lookup_business?query=2816464"

# find companies by director name
curl "https://onrc-api.adrianhomelab.com/lookup_director?name=popescu"
{
  "query": "DEDEMAN",
  "total": 2,
  "results": [
    {
      "companyName": "DEDEMAN SRL",
      "cui": "2816464",
      "registrationCode": "J1992002621040",
      "legalForm": "SRL",
      "county": "Bacău",
      "website": "www.dedeman.ro",
      "caenActivities": [ { "code": "0125", "activity": "…" } ],
      "directors": [ "PAVĂL I. DRAGOŞ", "PAVĂL ADRIAN" ],
      "status": [ { "code": "1048", "name": "funcțiune" } ]
    }
  ]
}

Where the data comes from

The registry is built from the official ONRC snapshot published on data.gov.ro — no scraping, no third-party vendor. The loaders stream the CKAN CSVs into SQLite and build an FTS5 full-text index with diacritic-insensitive folding, so popescu matches Popéscu and PAVĂL matches paval.

Repository layout

File

Purpose

api.py

FastAPI wrapper — the read-only public REST surface (+ landing page).

server.py

MCP server (Streamable HTTP) with all five tools.

monetization.py

Telemetry + a dormant freemium/rate-limit scaffold.

load_onrc.py

Download + load the ONRC CSV snapshot into SQLite.

load_nomenclatoare.py

Decode CAEN / status code tables.

load_financiare.py

Load the 2025 financial statements.

server.json

MCP Registry metadata (published as io.github.darksider4all/leadgen-mcp).

smithery.yaml

Smithery deployment config.

Run locally

python -m venv venv
venv/bin/pip install -r requirements.txt

# load the data (downloads the official snapshots — several GB)
venv/bin/python load_onrc.py --data-dir ./data --db ./data/onrc.db

# start the REST API
ONRC_DB=./data/onrc.db venv/bin/python api.py

# start the MCP server
ONRC_DB=./data/onrc.db venv/bin/python server.py --transport streamable-http --port 8766

Then hit http://127.0.0.1:8767/docs.

Notes on the data

  • Diacritic-insensitive search — Romanian ă â î ș ț are folded to their ASCII forms on both the index and the query.

  • CUI vs registration code — a numeric query is matched against the CUI (tax code) first, then the registration code.

  • Read-only — the public surface only exposes lookups; there are no write paths.

License

MIT — see LICENSE.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    Not graded
    maintenance
    Provides UK company lookups via Companies House, web scraping, and search tools designed to be context-efficient for AI agents. It includes integrated micro-payment monetization and supports data extraction and format conversion.
  • F
    license
    A
    quality
    D
    maintenance
    Enables AI agents to research companies and find contacts with structured data from multiple free sources, including company info, tech stack, and email addresses.
    3
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides real-time website audits, lead scoring, tech-stack detection, and local-business search for AI agents doing sales outreach and competitor research.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/darksider4all/leadgen-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server