norwegian-data-mcp
# norwegian-data-mcp
Norwegian public data in your AI assistant: companies, statistics, addresses, property. One MCP server, zero API keys, zero signup.
Ask Claude (or any MCP client) things like *"who is on the board of Equinor and what was their revenue last year?"* or *"how has Norwegian inflation moved this year?"* and it answers from the official registers, with sources.
## Install
Claude Code:
```
claude mcp add norway -- uvx norwegian-data-mcp
```
Claude Desktop (`claude_desktop_config.json`):
```json
{
"mcpServers": {
"norway": {
"command": "uvx",
"args": ["norwegian-data-mcp"]
}
}
}
```
Any other MCP client: run `uvx norwegian-data-mcp` (or `pip install norwegian-data-mcp` and run `norwegian-data-mcp`) as a stdio server.
## Tools
| Tool | Answers | Source |
|---|---|---|
| `search_companies` | "find companies that..." | Brønnøysundregistrene |
| `get_company` | full company record by orgnr | Brønnøysundregistrene |
| `get_company_roles` | board, CEO, auditor | Brønnøysundregistrene |
| `get_company_financials` | latest filed revenue, profit, balance sheet | Regnskapsregisteret |
| `get_group_structure` | subsidiaries and ownership stakes as a tree | Brønnøysundregistrene |
| `search_statistics` | find any of SSB's ~7,000 tables | SSB (Statistics Norway) |
| `get_table_info` | a table's variables and value codes | SSB |
| `get_statistics` | the numbers, as compact CSV | SSB |
| `get_key_series` | CPI, population, unemployment, house prices, wages, interest rates in one call | SSB |
| `get_exchange_rates` | daily NOK rates for any currency | Norges Bank |
| `search_address` | address to coordinates + gnr/bnr | Kartverket |
| `reverse_geocode` | coordinates to nearest addresses | Kartverket |
| `get_property` | cadastral parcel location and boundary | Kartverket |
| `get_place` | mountains, lakes, farms to coordinates | Kartverket |
## Try these
- "Who is on the board of Equinor, and what was their revenue last year?"
- "Find all breweries in Bergen. Any of them bankrupt?"
- "What's Norway's inflation rate right now, and how does the last year look?"
- "Population of Oslo over the last 10 years."
- "What are the coordinates and gnr/bnr of Karl Johans gate 22, Oslo?"
- "Norwegian mortgage and policy interest rates over the last two years."
- "How has the krone moved against the dollar and euro this month?"
- "Map Equinor's subsidiaries with ownership stakes."
## How responses look
Every tool returns a compact JSON envelope: the data (statistics come as CSV, the most token-efficient table format), a `hints` list that tells the model how to narrow or continue, and a `source` string naming the register and license. Responses are capped in size; SSB's dense JSON-stat2 cubes are flattened to plain tables with time on the rows.
When SSB closes a table (it happens: CPI table 03013 was replaced by 14700 in 2026), the server reads the succession note and follows or suggests the successor instead of failing.
## Data sources and licenses
| Register | License | Terms |
|---|---|---|
| SSB, Statistics Norway | [CC BY 4.0](https://www.ssb.no/en/diverse/lisens) | 30 requests/minute, respected client-side |
| Brønnøysundregistrene (Enhetsregisteret, Regnskapsregisteret) | [NLOD 2.0](https://data.norge.no/nlod/en/2.0) | open API, fair use |
| Norges Bank (exchange rates) | [NLOD 2.0](https://data.norge.no/nlod/en/2.0) | open SDMX API |
| Kartverket (addresses, cadastre, place names) | [CC BY 4.0](https://www.kartverket.no/en/api-and-data/terms-of-use) | © Kartverket |
All four are open government data with no key or registration. Every response carries its attribution, so the model can cite it.
### What this server will not do
- **Property owners, buildings, valuations, grunnbok**: Norway keeps these behind a licensed Matrikkel agreement that private individuals cannot apply for. No open API exists, so no tool pretends otherwise.
- **Shareholder registers and tax lists**: no open APIs exist; tax-list searches are logged and the searched person is notified.
- **Person search**: looking up all roles a person holds across companies is legally restricted (enhetsregisterloven §9-1). Per-company roles are the lawful slice and that is what `get_company_roles` serves.
- **Historical financials**: the open Regnskapsregisteret API serves the latest filed year only; the tool links the official annual-report PDF for the rest.
## Development
```
python -m venv .venv && .venv/bin/pip install -e '.[dev]'
.venv/bin/pytest # offline, fixtures only
.venv/bin/pytest -m live --override-ini addopts='' # live smoke against the real APIs
```
Runtime dependencies are `mcp` and `httpx`, nothing else. Responses are cached with per-source TTLs (in memory plus `~/.cache/norwegian-data-mcp`, disable with `NORWEGIAN_DATA_MCP_CACHE=off`), and a stale cached copy is served with a note if a register is briefly unreachable.
## Roadmap
- plot area via the Teig WFS, daily policy-rate series, elevation and kommune info tools
- streamable HTTP transport for hosted use
<!-- mcp-name: io.github.7nashinick/norwegian-data-mcp -->
TDQS
Scored across 14 tools
Every tool targets a clearly distinct resource or action, and descriptions explicitly delimit boundaries (e.g., search_companies vs. get_company, search_address vs. get_place, get_statistics vs. get_key_series). The statistics pipeline (search, table info, fetch, shortcut) and address/property tools have non-overlapping roles that an agent can follow without confusion.
All 14 tool names use consistent snake_case with a verb_noun pattern (search_companies, get_company_roles, reverse_geocode, etc.). There are no mixed conventions or ambiguous prefixes.
14 tools is within the ideal range for a multi-domain public-data server, and each tool covers a necessary read operation (search, get, or reverse lookup) for companies, statistics, addresses, or exchange rates. No tool feels redundant or out of place.
The surface covers core workflows for companies (search, full record, roles, financials, group), statistics (discovery, metadata, fetch, key series), and addresses/properties/places. Minor gaps remain, such as no shareholder/ownership lookup and only the most recent financial year, which could cause dead ends for some ownership or historical queries.