{
  "markdown": "# hvilkenAI MCP Server\n\n[![Glama Quality Score](https://glama.ai/mcp/servers/erorund/hvilkenai-mcp/badge)](https://glama.ai/mcp/servers/erorund/hvilkenai-mcp)\n\nDaily Scandinavian AI language quality benchmark — Norwegian, Swedish, Danish.\n\n## What this does\n\nhvilkenAI benchmarks AI models daily on practical Scandinavian language tasks.\n12+ models are tested every day, selected from a pool of over 350 AI models\navailable through OpenRouter. This MCP server lets AI assistants access\nfresh benchmark data directly.\n\n**Use cases:**\n- \"Which AI is best at Norwegian right now?\"\n- \"Compare GPT-4o vs Claude on Swedish\"\n- \"What's the cheapest model that handles Danish well?\"\n- \"Show me how Gemini has performed this week\"\n\n## Available tools\n\n### get_daily_benchmark\nGet today's benchmark results for AI models on Scandinavian languages.\n\n| Parameter | Type | Values | Default |\n|-----------|------|--------|---------|\n| `language` | string | `no`, `sv`, `da` | `no` |\n| `tier` | string | `all`, `premium`, `midrange`, `budget` | `all` |\n\n**Returns:** Model rankings with scores, pricing, and speed. Free tier returns yesterday's top 3; Pro returns today's full list.\n\n### get_model_history\nTrack a specific model's performance over time.\n\n| Parameter | Type | Values | Default |\n|-----------|------|--------|---------|\n| `model_name` | string | Model name or partial match, e.g. `\"Claude Sonnet\"`, `\"GPT-4o\"`, `\"gemini\"` | *(required)* |\n| `language` | string | `no`, `sv`, `da` | `no` |\n| `days` | number | 1–30 (free tier: max 3) | `7` |\n\n**Returns:** Daily scores and trends for the specified model.\n\n### get_orchestrator_ranking\nFind the best model for AI agent orchestration and multi-agent systems.\n\n| Parameter | Type | Values | Default |\n|-----------|------|--------|---------|\n| `language` | string | `no`, `sv`, `da` | `no` |\n\n**Returns:** Models ranked by combined language quality and instruction-following ability.\n\n### get_recommendation\nGet a model recommendation tailored to your specific needs and budget.\n\n| Parameter | Type | Values | Default |\n|-----------|------|--------|---------|\n| `use_case` | string | `writing`, `coding`, `research`, `agent`, `general` | `general` |\n| `language` | string | `no`, `sv`, `da` | `no` |\n| `budget` | string | `free`, `cheap`, `any` | `any` |\n\n**Returns:** Best model match with reasoning. Pro tier returns top 3 with full details.\n\n### get_weekly_summary\nGet the weekly benchmark summary with trends and reliability analysis.\n\n| Parameter | Type | Values | Default |\n|-----------|------|--------|---------|\n| `language` | string | `no`, `sv`, `da` | `no` |\n| `week` | string | Format `YYYY-WW`, e.g. `\"2026-21\"` | current week |\n\n**Returns:** Winner, most reliable model, and key observations for the week.\n\n## Quick start\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"hvilkenai\": {\n      \"type\": \"streamablehttp\",\n      \"url\": \"https://mcp.hvilkenai.no/mcp\"\n    }\n  }\n}\n```\n\nClaude Desktop supports OAuth 2.1 — you will be prompted to connect with free or Pro access when you first use the server.\n\n### Claude Code (CLI)\n\n```bash\nclaude mcp add --transport http hvilkenai https://mcp.hvilkenai.no/mcp\n```\n\n### Cursor / VS Code\n\n```json\n{\n  \"mcpServers\": {\n    \"hvilkenai\": {\n      \"url\": \"https://mcp.hvilkenai.no/mcp\"\n    }\n  }\n}\n```\n\n### Direct API\n\n```bash\ncurl -X POST https://mcp.hvilkenai.no/mcp \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"jsonrpc\":\"2.0\",\"method\":\"tools/list\",\"id\":1}'\n```\n\n## Authentication\n\n**Free tier** — no API key required:\n- 24-hour delayed data\n- Top 3 models per language\n- 100 requests/hour\n\n**Pro** — requires API key (Bearer token):\n- Real-time data (updated daily at 07:30 CET)\n- All models, all languages\n- Historical data up to 30 days\n- Higher rate limits\n\nGet an API key at [hvilkenai.no/priser/](https://hvilkenai.no/priser/)\n\nFor Pro access, add your API key as a Bearer token:\n\n```json\n{\n  \"mcpServers\": {\n    \"hvilkenai\": {\n      \"type\": \"streamablehttp\",\n      \"url\": \"https://mcp.hvilkenai.no/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n## Example interaction\n\n> **You:** Which AI model is best at Norwegian today?\n>\n> **Claude (using hvilkenAI):** Based on today's benchmark from hvilkenai.no,\n> [model name] leads with a score of X.X, followed by...\n\n## About the benchmark\n\n- **Updated daily** at 07:30 CET\n- **Three languages:** Norwegian (Bokmål), Swedish, Danish\n- **Practical tasks:** Real-world language use, not academic tests\n- **Broad coverage:** 12+ models selected daily from over 350 AI models\n- **Independent:** No sponsorships, no affiliate deals\n- **Proprietary methodology:** Scoring uses a proprietary weighting system\n\nData source: [hvilkenai.no](https://hvilkenai.no)\n\n## Links\n\n- **Website:** [hvilkenai.no](https://hvilkenai.no)\n- **Glama:** [glama.ai/mcp/servers/erorund/hvilkenai-mcp](https://glama.ai/mcp/servers/erorund/hvilkenai-mcp)\n- **Integrations page:** [hvilkenai.no/integrasjoner/](https://hvilkenai.no/integrasjoner/)\n- **Server URL:** `https://mcp.hvilkenai.no/mcp`\n- **Health check:** `https://mcp.hvilkenai.no/health`\n\n## License\n\nMIT\n",
  "bytes": 5188,
  "sha": "3c7eb2745bce56b91581ca369de0ae5ffc34576c046fcbd95db239556cd740a9",
  "repo_slug": "erorund/hvilkenai-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_erorund_hvilkenai_mcp_a9fd7daa/readme"
}