I Stopped Scraping Business Directories and Built an MCP Server on Official Registry Data
I Stopped Scraping Business Directories and Built an MCP Server on Official Registry Data For a long time I built B2B lead-generation tools the way everyone does: scrape a directory, fight the anti-bot, re-scrape when the layout changes, pray the data is current. Then I found out the Romanian government publishes the entire company registry as open data — 4.2 million firms, refreshed monthly,…
The author of the story decided to stop scraping business directories and instead built an MCP server using official registry data from the Romanian government. This change brought several benefits, including avoiding fragile and slow scraping methods, eliminating legal grey areas, and receiving up-to-date data. The Romanian government publishes the entire company registry as open data, containing 4.2 million firms with details like legal status, activity codes, and directors.
The author explains how they turned this open-data snapshot into a self-hosted MCP server by utilizing CKAN, a government data portal, and constructing a pipeline consisting of CKAN, SQLite, and MCP. This pipeline involves downloading the data via the CKAN API, streaming-loading it into SQLite, decoding the data using nomenclator tables, and exposing it through MCP tools.
The three MCP tools provided are: 1. lookup_business, which enables searching for companies by name or CUI and returns enriched results with decoded CAEN activities, directors, and status. 2. extract_contacts, which crawls a company's website to extract contact information like emails, phone numbers, and social media profiles. 3.
The fast MCP server, which runs on the author's homelab box and provides the three aforementioned tools.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — it may contain errors, so check the original before relying on it.
