# Norway Archives (pypi · norway-archives-mcp)

Norway's church books, censuses and scans, National Library books, and place names.

- Trust score: 80/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `norway-archives-mcp`: 80/100 (this document), [markdown](https://verifymcp.io/servers/ianderso-norway-archives-mcp/norway-archives-mcp.md), [page](https://verifymcp.io/servers/ianderso-norway-archives-mcp/norway-archives-mcp)

## Channel facts

- Registry: `pypi`
- Package: `norway-archives-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 34 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to ianderso/norway-archives-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2006 tokens (~154/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Norway Archives MCP server?

Norway Archives runs locally as a PyPI package, launched with uvx norway-archives-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add ianderso-norway-archives-mcp -- uvx norway-archives-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ianderso-norway-archives-mcp": {
      "command": "uvx",
      "args": [
        "norway-archives-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ianderso-norway-archives-mcp": {
      "command": "uvx",
      "args": [
        "norway-archives-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ianderso-norway-archives-mcp -- uvx norway-archives-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ianderso-norway-archives-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "norway-archives-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ianderso-norway-archives-mcp --command uvx --arg norway-archives-mcp
```

### Hermes

```yaml
mcp_servers:
  ianderso-norway-archives-mcp:
    command: "uvx"
    args: ["norway-archives-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ianderso-norway-archives-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "norway-archives-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ianderso-norway-archives-mcp -t stdio -c uvx -a norway-archives-mcp
```

### Other

```json
{
  "mcpServers": {
    "ianderso-norway-archives-mcp": {
      "command": "uvx",
      "args": [
        "norway-archives-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-14 (score 80, +45)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-10-13 (score 35, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-12 (score 50)

First indexed and scored.

## MCP tools (13)

### `da_search_persons` (~288 tokens)

Search Digitalarkivet's transcribed records for a person.

Covers transcribed church-book entries, censuses (1801-1920), emigrant lists
and more. Each hit gives the record's address for da_get_record. Only
transcribed lists are searched.

Input parameters:

- `birth_place` (string): Birthplace as written in the record.
- `birth_year_from`: Earliest birth year.
- `birth_year_to`: Latest birth year.
- `domicile` (string): Residence or farm as written.
- `event_year_from`: Earliest event year.
- `event_year_to`: Latest event year.
- `first_name` (string): Given name(s).
- `last_name` (string): Surname; * is a wildcard, e.g. 'Rønning*'.
- `list_type` (string): One list, by code or label: dp baptisms, kf confirmations, vi marriages, gr burials, uf out-migrated, if in-migrated, fl in/out-migrated.
- `municipality` (string): Historical municipality: name or four-digit number (see municipalities).
- `name_variants` (boolean): Also match Digitalarkivet's name variants.
- `page` (integer): Result page, 50 hits each.
- `refresh` (boolean): True asks again instead of using the cached answer, and replaces it.

### `da_get_record` (~112 tokens)

Read one transcribed record: its fields, everyone named in it, and its scanned page.

\`scanned_pages` gives the permanent page id to pass to da_download_page.

Input parameters:

- `record` (string, required): A record address from da_search_persons, or its path, e.g. 'view/255/pd00000024592808' or 'census/person/pf01038322000172'.
- `refresh` (boolean): True asks again instead of using the cached answer, and replaces it.

### `da_search_sources` (~184 tokens)

Find sources (church books, censuses, probate records) by place, period and list.

Each source says which lists it holds, which are scanned and which are
searchable. A list that is scanned but not searchable can still be read
page by page with da_get_source and da_list_pages.

Input parameters:

- `list_type` (string): Only sources holding this list, by code or label (e.g. kf, uf).
- `municipality` (string): Historical municipality: name or four-digit number.
- `page` (integer): Result page.
- `query` (string): Words in the source's title, e.g. a parish name.
- `refresh` (boolean): True asks again instead of using the cached answer, and replaces it.
- `year_from`: Earliest year the source covers.
- `year_to`: Latest year the source covers.

### `da_get_source` (~102 tokens)

Describe one source and map its scans: archive reference, images, where each list starts.

Sections are the lists in the book (baptisms, confirmations, out-migrated…)
with the image each begins on; a list usually runs until the next starts.

Input parameters:

- `refresh` (boolean): True asks again instead of using the cached answer, and replaces it.
- `source_id` (integer, required): The source id, from da_search_sources or a record.

### `da_list_pages` (~126 tokens)

List a source's scanned pages in order, with each page's permanent id and permalink.

For reading a list nobody transcribed: pass page ids to da_download_page.

Input parameters:

- `count` (integer): How many images, at most 100.
- `refresh` (boolean): True asks again instead of using the cached answer, and replaces it.
- `section` (string): Start where this list begins instead (code or label, e.g. kf).
- `source_id` (integer, required): The source id.
- `start` (integer): First image number, 1-based.

### `da_download_page` (~164 tokens)

Download one scanned page from Digitalarkivet so it can be read.

This is the step that turns a hit into evidence. Returns the citation
(source, archive reference, image number, permanent link). Census pages
(ft… ids) come at full resolution only.

Input parameters:

- `destination` (string, required): Absolute path of a new .jpg file. The directory must exist and the file must not: nothing is overwritten.
- `image`: …and the image number, 1-based.
- `max_pixels` (integer): Longest side in pixels; 0 for full resolution.
- `page_id` (string): Permanent page id, e.g. 'kb20070419660152' or 'ft2009…'.
- `source_id`: Instead: the source id…

### `nb_search` (~191 tokens)

Search the National Library of Norway's books, newspapers and more.

Each item says where it can be read: everywhere, Norway only, or the library
only. nb_search_inside finds the page in any of them.

Input parameters:

- `digitised_only` (boolean): Only digitised items.
- `full_text` (boolean): Search inside the text, not only titles.
- `media_type` (string): books, newspapers, journals, maps, letters, manuscripts, pictures, private archives; empty for all.
- `page` (integer): Result page, 20 items each.
- `query` (string, required): Words to find; quotes for a phrase, e.g. '"Røros kobberverk"'.
- `refresh` (boolean): True asks again instead of using the cached answer, and replaces it.
- `year_from`: Earliest year of publication.
- `year_to`: Latest year of publication.

### `nb_search_inside` (~104 tokens)

Find the pages of one book or newspaper that mention a word, with snippets.

Works for Norway-only items too: the printed page number tells you what to
request from a library even when the page cannot be shown here.

Input parameters:

- `item_id` (string, required): The item id from nb_search (32 hex characters).
- `max_snippets` (integer): Most snippets, 1 to 50.
- `query` (string, required): Word or name to find inside the item.

### `nb_get_page` (~108 tokens)

Read one page of a National Library item: its OCR text where it is open, and its citation.

Input parameters:

- `image`: Instead: the image number, 1-based.
- `include_text` (boolean): Return the page's OCR text when open.
- `item_id` (string, required): The item id from nb_search.
- `page` (string): The printed page number, as a snippet gives it.
- `page_id` (string): Instead: the page id from nb_search_inside.

### `nb_download_page` (~125 tokens)

Download one page image of a National Library item that is open where you are.

Input parameters:

- `destination` (string, required): Absolute path of a new .jpg file. The directory must exist and the file must not: nothing is overwritten.
- `image`: Instead: the image number, 1-based.
- `item_id` (string, required): The item id from nb_search.
- `max_pixels` (integer): Longest side in pixels; 0 for full resolution.
- `page` (string): The printed page number.
- `page_id` (string): Instead: the page id.

### `place_names` (~140 tokens)

Find farms, hamlets and other places in Kartverket's official place-name register.

Gives today's spelling, type (farm, village, lake…), municipality and
coordinates. Old spellings in records often differ: try a wildcard or fuzzy.

Input parameters:

- `county` (string): Today's county: name or number.
- `fuzzy` (boolean): Also return names that sound alike.
- `limit` (integer): Most names, 1 to 100.
- `municipality` (string): Today's municipality: name or number (merged since 2020).
- `name` (string, required): The name; * is a wildcard, e.g. 'Røros*'.

### `municipalities` (~86 tokens)

Look up Digitalarkivet's historical municipalities and their numbers. Makes no network call.

The da_ tools filter by these (as they stood around 1947), not by today's
merged municipalities. Also lists the list-type codes.

Input parameters:

- `county` (string): An old county name or two-digit number.
- `query` (string): Part of a name, or a four-digit number.

### `cache_status` (~27 tokens)

Report this session's requests, by service, the Digitalarkivet budget, and cache use.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/ianderso-norway-archives-mcp/norway-archives-mcp#diagnostics

## Score history

- 2026-10-18: 80
- 2026-10-17: 80
- 2026-10-16: 80
- 2026-10-15: 80
- 2026-10-14: 80
- 2026-10-13: 35
- 2026-10-12: 50

## Common questions

### What is the Norway Archives MCP server?

Norway Archives is an MCP server listed in the public MCP registry as io.github.ianderso/norway-archives-mcp. Norway's church books, censuses and scans, National Library books, and place names. This page covers its PyPI package (norway-archives-mcp).

### Is the Norway Archives MCP server safe to use?

Norway Archives scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Norway Archives MCP server expose?

Norway Archives exposes 13 tools: da_search_persons, da_get_record, da_search_sources, da_get_source, da_list_pages, and 8 more. Their descriptions and schemas cost roughly 1,757 tokens of context every time the server is loaded.

### Is the Norway Archives MCP server still maintained?

Norway Archives is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Norway Archives MCP server under?

Norway Archives declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/norway-archives-mcp/
- Socket report: https://socket.dev/pypi/package/norway-archives-mcp
- Repository: https://github.com/ianderso/norway-archives-mcp
- Changelog RSS feed: https://verifymcp.io/servers/ianderso-norway-archives-mcp/norway-archives-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ianderso-norway-archives-mcp/norway-archives-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ianderso-norway-archives-mcp/norway-archives-mcp