Tutorial: eInnsyn (Norwegian Public Records)

Government

Data source: eInnsyn (einnsyn.no)

Overview

eInnsyn (Norwegian Public Records) wraps eInnsyn (einnsyn.no), handling authentication, pagination, and rate limits for you. This tutorial covers all 6 tools with working code examples you can copy and run.

Prerequisites

Sign up at https://context.gnist.ai/signup for a free API key (100 calls/day).
Choose your integration method: MCP protocol or REST API.

Connect via MCP

Add to your MCP client config (Claude Desktop, Cursor, etc.):

MCP Config

{
  "mcpServers": {
    "gnist-einnsyn": {
      "url": "https://context.gnist.ai/mcp/einnsyn/",
      "headers": {
        "Gnist-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Tools (6)

`search_records`

Search Norwegian public records — journal entries, case folders, and meeting documents. eInnsyn is Norway's official public records portal. All government agencies are required to publish their correspondence journals here. This tool searches across all agencies. Args: query: Free-text search. Supports exact match with quotes, exclusion with minus. entity: Filter by type: 'Journalpost', 'Saksmappe', 'Moetemappe', or 'Moetesak'. limit: Results per page (1-100, default 25). journal_date_from: Filter by journal date start (ISO date, e.g. '2025-01-01'). journal_date_to: Filter by journal date end (ISO date). journalpost_type: Filter journal type: 'inngaaende_dokument', 'utgaaende_dokument', 'organinternt_dokument_uten_oppfoelging', 'organinternt_dokument_for_oppfoelging'. sort_by: Sort order (default 'score'). Options: 'score', 'journaldato', 'publisertDato', 'tittel', 'administrativEnhetNavn'. Returns: Dict with 'count', 'items' list, and 'next' cursor for pagination.

Parameter	Type	Required	Description
`query`	string	required	Free-text search. Supports exact match with quotes, exclusion with minus.
`entity`	any	optional	Filter by type: 'Journalpost', 'Saksmappe', 'Moetemappe', or 'Moetesak'.
`limit`	integer	optional	Results per page (1-100, default 25). (default: `25`)
`journal_date_from`	any	optional	Filter by journal date start (ISO date, e.g. '2025-01-01').
`journal_date_to`	any	optional	Filter by journal date end (ISO date).
`journalpost_type`	any	optional	Filter journal type: 'inngaaende_dokument', 'utgaaende_dokument', 'organinternt_dokument_uten_oppfoelging', 'organinternt_dokument_for_oppfoelging'.
`sort_by`	string	optional	Sort order (default 'score'). Options: 'score', 'journaldato', 'publisertDato', 'tittel', 'administrativEnhetNavn'. (default: `score`)

curl -X POST "https://context.gnist.ai/mcp/einnsyn/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "search_records", "arguments": {"query": "renewable energy"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/einnsyn/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'query': 'renewable energy'},
            'name': 'search_records'}},
)
print(resp.json())

`get_journal_entry`

Get a specific journal entry (journalpost) from eInnsyn. Returns the full entry with correspondents (senders/recipients) and attached document metadata. Use the ID from search_records results. Args: journalpost_id: The journal entry ID (e.g. 'jp_...' or a UUID). Returns: Full journal entry with title, dates, correspondents, and documents.

Parameter	Type	Required	Description
`journalpost_id`	string	required	The journal entry ID (e.g. 'jp_...' or a UUID).

curl -X POST "https://context.gnist.ai/mcp/einnsyn/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "get_journal_entry", "arguments": {"journalpost_id": "'jp_...'"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/einnsyn/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'journalpost_id': "'jp_...'"},
            'name': 'get_journal_entry'}},
)
print(resp.json())

`get_case_folder`

Get a case folder (saksmappe) from eInnsyn. A case folder groups related journal entries for a government case. Returns the case metadata and list of associated journal entry IDs. Args: saksmappe_id: The case folder ID (e.g. 'sm_...' or a UUID). Returns: Case folder with title, case number, and journal entry references.

Parameter	Type	Required	Description
`saksmappe_id`	string	required	The case folder ID (e.g. 'sm_...' or a UUID).

curl -X POST "https://context.gnist.ai/mcp/einnsyn/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "get_case_folder", "arguments": {"saksmappe_id": "'sm_...'"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/einnsyn/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'saksmappe_id': "'sm_...'"},
            'name': 'get_case_folder'}},
)
print(resp.json())

`list_organizations`

List government organizations registered in eInnsyn. Returns organizational units (ministries, agencies, municipalities) that publish records to eInnsyn. Args: limit: Number of organizations to return (1-100, default 25). Returns: Dict with 'count', 'units' list (id, name, parent), and 'next' cursor.

Parameter	Type	Required	Description
`limit`	integer	optional	Number of organizations to return (1-100, default 25). (default: `25`)

curl -X POST "https://context.gnist.ai/mcp/einnsyn/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "list_organizations", "arguments": {"limit": 25}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/einnsyn/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'limit': 25}, 'name': 'list_organizations'}},
)
print(resp.json())

`get_publication_statistics`

Get aggregate publication statistics for eInnsyn records. Shows how many records have been published, how many include full text, and download counts. Useful for transparency reporting and trend analysis. Args: interval: Aggregation interval: 'hour', 'day', 'week', 'month', 'year'. date_from: Start date (ISO, e.g. '2025-01-01'). Defaults to one year ago. date_to: End date (ISO). Defaults to today. Returns: Dict with 'summary' (totals) and 'time_series' (bucketed counts).

Parameter	Type	Required	Description
`interval`	string	optional	Aggregation interval: 'hour', 'day', 'week', 'month', 'year'. (default: `month`)
`date_from`	any	optional	Start date (ISO, e.g. '2025-01-01'). Defaults to one year ago.
`date_to`	any	optional	End date (ISO). Defaults to today.

curl -X POST "https://context.gnist.ai/mcp/einnsyn/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "get_publication_statistics", "arguments": {"interval": "month"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/einnsyn/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'interval': 'month'},
            'name': 'get_publication_statistics'}},
)
print(resp.json())

`report_feedback`

Report a bug, feature request, or general feedback for this data source. Use this when something doesn't work as expected, when you'd like a new feature, or when you have suggestions for improvement. Args: feedback: Describe the issue or suggestion. feedback_type: One of 'bug', 'feature_request', or 'general'.

Parameter	Type	Required	Description
`feedback`	string	required
`feedback_type`	string	optional	(default: `general`)

curl -X POST "https://context.gnist.ai/mcp/einnsyn/" \
  -H "Content-Type: application/json" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "report_feedback", "arguments": {"feedback": "example"}}}'

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/einnsyn/",
    headers={"Gnist-API-Key": "YOUR_API_KEY"},
    json={'id': 1,
 'jsonrpc': '2.0',
 'method': 'tools/call',
 'params': {'arguments': {'feedback': 'example'}, 'name': 'report_feedback'}},
)
print(resp.json())

Common Patterns

Search then retrieve
Use search_records to find items, then get_journal_entry to get full details. This two-step pattern is common for exploring data before drilling down.

Pagination
Several tools support limit, offset, or page parameters. Start with small limits during development, then increase for production queries.

Date range filtering
Use date range parameters to narrow results to a specific time window. Dates are typically in YYYY-MM-DD format.

FAQ

What data does eInnsyn (Norwegian Public Records) provide?

Norwegian public records — journal entries, case folders, and meeting documents from government agencies. It exposes 6 tools: search_records, get_journal_entry, get_case_folder, list_organizations, get_publication_statistics, report_feedback.

What do I need to get started?

A Gnist API key (free tier: 100 calls/day). Sign up at https://context.gnist.ai/signup.

What format does the eInnsyn (Norwegian Public Records) API return?

JSON, via either MCP protocol (JSON-RPC 2.0) or REST API.