Claude MarketplacesSubmit
erorund avatar

Hvilkenai Mcp

erorund/hvilkenai-mcp

Connects to the hvilkenAI benchmarking service that tests 12+ language models daily on Norwegian, Swedish, and Danish tasks. You get five tools: query today's benchmark results by language and tier, pull weekly summaries with winners and reliability stats, check historical scores for specific models, view combined orchestrator rankings, and get model recommendations based on use case and budget. Tests run daily at 07:30 CET and cover language quality, instruction following, speed, and cost. Reach for this when you need current data on which models actually perform well on Scandinavian languages, especially if you're building customer service bots or content tools for Nordic markets.

tools
5
transport
HTTP
last updated
May 26, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://mcp.hvilkenai.no/mcp --name hvilkenai-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http hvilkenai-mcp https://mcp.hvilkenai.no/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 5 tools

Verified live against the running server on Nov 6, 2026.

get_daily_benchmarkReturnerer 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.2 params

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.

Parameters* required
languagestring
Språk for benchmark (no=norsk, sv=svensk, da=dansk). Standard: noone of no · sv · da
tierstring
Filtrer etter prisnivå. Standard: allone of all · premium · midrange · budget
get_weekly_summaryUkens oppsummering av AI-benchmark – vinner, trender og pålitelighetsanalyse. Rapport genereres hver fredag.2 params

Ukens oppsummering av AI-benchmark – vinner, trender og pålitelighetsanalyse. Rapport genereres hver fredag.

Parameters* required
languagestring
Språk. Standard: noone of no · sv · da
weekstring
Ukenummer i format "ÅÅÅÅ-UU", f.eks. "2026-21". Standard: nåværende uke
get_model_historyHenter historisk benchmark-data for én AI-modell over tid. Viser score-utvikling per dag. Gratis: siste 3 dager. Betalt: opptil 30 dager.3 params

Henter historisk benchmark-data for én AI-modell over tid. Viser score-utvikling per dag. Gratis: siste 3 dager. Betalt: opptil 30 dager.

Parameters* required
daysnumber
Antall dager historikk (1–30). Standard: 7. Gratis: maks 3 dager.
languagestring
Språk. Standard: noone of no · sv · da
model_name*string
Navn eller del av navn på modellen, f.eks. "Claude Sonnet", "GPT-4o" eller "gemini"
get_orchestrator_rankingRangering 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.1 params

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.

Parameters* required
languagestring
Språk. Standard: noone of no · sv · da
get_recommendationAnbefaler 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.3 params

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.

Parameters* required
budgetstring
Budsjett: free (gratis API), cheap (ikke premium), any (alle). Standard: anyone of free · cheap · any
languagestring
Språk. Standard: noone of no · sv · da
use_casestring
Bruksområde: writing (skriving), coding (koding), research (research/faktasjekk), agent (AI-agenter/orkestrator), general (generell). Standard: generalone of writing · coding · research · agent · general

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

hvilkenAI MCP Server

Glama Quality Score

Daily Scandinavian AI language quality benchmark — Norwegian, Swedish, Danish.

What this does

hvilkenAI benchmarks AI models daily on practical Scandinavian language tasks. 12+ models are tested every day, selected from a pool of over 350 AI models available through OpenRouter. This MCP server lets AI assistants access fresh benchmark data directly.

Use cases:

  • "Which AI is best at Norwegian right now?"
  • "Compare GPT-4o vs Claude on Swedish"
  • "What's the cheapest model that handles Danish well?"
  • "Show me how Gemini has performed this week"

Available tools

get_daily_benchmark

Get today's benchmark results for AI models on Scandinavian languages.

ParameterTypeValuesDefault
languagestringno, sv, dano
tierstringall, premium, midrange, budgetall

Returns: Model rankings with scores, pricing, and speed. Free tier returns yesterday's top 3; Pro returns today's full list.

View the full README on GitHub

Details

Repository
github.com/erorund/hvilkenai-mcp
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026