# io.github.erorund/hvilkenai-mcp

> Daily Scandinavian AI benchmark — Norwegian, Swedish, Danish. 12+ models tested.

- name: io.github.erorund/hvilkenai-mcp
- version: 1.0.0
- connection class: R2 (oauth_consent_once)
- trust: 87/100
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.erorund%2Fhvilkenai-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.erorund%2Fhvilkenai-mcp/tools

**An agent can connect after a one-time OAuth consent by a human.** Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "hvilkenai-mcp": {
      "type": "http",
      "url": "https://mcp.hvilkenai.no/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 65
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-98% ~updated-147d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: 83 (weight 15)

- pass `auth.prm`: Protected Resource Metadata (RFC 9728) published
- pass `auth.as_metadata`: authorization server metadata reachable
- warn `auth.cimd`: only Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_daily_benchmark (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_weekly_summary (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_model_history (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 628 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history not recorded yet

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 628 tokens to load them all
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.erorund/hvilkenai-mcp.svg)](https://protogrid.dev/servers/io.github.erorund/hvilkenai-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.hvilkenai.no/mcp (streamable-http, auth oauth2, reachable true, uptime30d 0.9830508)

## Packages

_none_

## Tools (5)

- `get_daily_benchmark`: Returnerer benchmark-resultater for AI-modeller på skandinaviske språk. Gratis: gårsdagens data (24t forsinkelse), topp 3 modeller. Med API-nøkkel: sanntidsdata, alle modeller. Oppdateres daglig kl 07:30 CET.
- `get_model_history`: Henter historisk benchmark-data for én AI-modell over tid. Viser score-utvikling per dag. Gratis: siste 3 dager. Betalt: opptil 30 dager.
- `get_orchestrator_ranking`: Rangering av AI-modeller egnet som orkestrator i multi-agent-systemer. Score = (norsk × instruksjon / 25) × 10. Gratis: gårsdagens data, topp 3. Med API-nøkkel: sanntidsdata, alle modeller.
- `get_recommendation`: Anbefaler beste AI-modell for et spesifikt bruksområde og budsjett. Gratis: beste valg basert på gårsdagens data (24t forsinkelse). Med API-nøkkel: sanntidsdata, topp 3 med begrunnelse.
- `get_weekly_summary`: Ukens oppsummering av AI-benchmark – vinner, trender og pålitelighetsanalyse. Rapport genereres hver fredag.