regon-mcp
Provides clean, typed access to the Polish REGON business register (GUS BIR1), enabling AI assistants to look up companies by NIP, REGON, or KRS and retrieve structured data like name, address, and legal form.
README
regon-mcp
<!-- mcp-name: io.github.SmartMobileHouse/regon-mcp -->
A Model Context Protocol server that gives AI assistants clean, typed access to the Polish REGON business register (GUS BIR1). Look up any Polish company by NIP, REGON, or KRS and get back structured data — name, address, legal form, activity codes — without touching the underlying SOAP API.
The official GUS BIR1 API is a WCF SOAP
service with WS-Addressing, MTOM multipart responses, an HTTP-header session
token, and XML-nested-inside-XML result payloads. regon-mcp hides all of that
behind a handful of simple tools.
Built and maintained by Smart Mobile House — secure AI implementation for enterprise.
Tools
| Tool | Description |
|---|---|
search_by_nip(nip) |
Look up an entity by 10-digit NIP (tax id). |
search_by_regon(regon) |
Look up an entity by 9- or 14-digit REGON. |
search_by_krs(krs) |
Look up an entity by 10-digit KRS (court register). |
search_bulk(identifiers, id_type) |
Look up up to 20 entities of one type at once. |
get_full_report(regon, report_type) |
Fetch a detailed report for one entity. |
list_report_types() |
List valid report names, with guidance on which to use. |
Every response includes a source block that names the register (REGON / GUS),
the environment, and a UTC retrieved_at timestamp — so downstream use can cite
the data correctly, as GUS requires.
Quick start
No install needed — run it straight from the repo with uv:
uvx --from git+https://github.com/SmartMobileHouse/regon-mcp regon-mcp
By default it uses the public test key against the anonymized GUS test
database, so it runs with zero setup. For live data, request a free USER_KEY
from regon_bir@stat.gov.pl and set the environment variables below.
Use it in Claude Desktop / Claude Code
Add to your MCP config (e.g. claude_desktop_config.json or a project
.mcp.json):
{
"mcpServers": {
"regon": {
"command": "uvx",
"args": ["--from", "git+https://github.com/SmartMobileHouse/regon-mcp", "regon-mcp"],
"env": {
"REGON_API_KEY": "your-user-key",
"REGON_ENV": "prod"
}
}
}
}
During development, point it at a local checkout instead:
{
"mcpServers": {
"regon": {
"command": "uvx",
"args": ["--from", "/absolute/path/to/regon-mcp", "regon-mcp"],
"env": { "REGON_API_KEY": "abcde12345abcde12345" }
}
}
}
Configuration
| Variable | Default | Description |
|---|---|---|
REGON_API_KEY |
public test key | Your GUS BIR USER_KEY. |
REGON_ENV |
test |
test (anonymized data) or prod (live data). |
REGON_TIMEOUT |
30 |
HTTP timeout in seconds. |
Use REGON_ENV=prod only with a real USER_KEY; the test key works only
against the test environment.
Development
git clone https://github.com/SmartMobileHouse/regon-mcp
cd regon-mcp
uv sync # create the venv and install deps
uv run pytest # offline tests: validation, parsing, mocked client,
# and an in-memory MCP tool-discovery smoke test.
# (network tests are deselected by default)
uv run regon-mcp # run the server over stdio
# Live tests against the GUS endpoint (deselected unless opted in):
REGON_RUN_NETWORK=1 uv run pytest -m network # session lifecycle (test env)
REGON_PROD_KEY=<your-key> uv run pytest -m network # positive-control on live data
The client is a small hand-rolled SOAP layer over httpx (see
src/regon_mcp/client.py) — no heavyweight SOAP stack, no runtime WSDL fetch.
Notes & limitations
- The GUS test database is anonymized and returns little or no entity data.
Meaningful results require a production
USER_KEYwithREGON_ENV=prod. - Respect the GUS terms of use and rate limits. This project is an independent open-source client and is not affiliated with or endorsed by GUS.
- Data belongs to GUS. When you present it, cite REGON / GUS with the
retrieval date (surfaced in every response's
sourceblock).
License
MIT © Smart Mobile House
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.