Polyglot AI Board
Read-only: which LLM is best in 7 languages (zh, ko, nb, de, nl, es, pt), from public benchmarks.
我該用這個嗎
品質與安全性
B
根據工具定義與協定合規性的自動化分析。
上下文成本
~212Token(工具定義)
~203 B典型回應大小
極小的注意力影響(128k 上下文的 0.17%)
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"board": {
"url": "https://polyglot-ai-board.vercel.app/api/mcp"
}
}
}遠端端點
https://polyglot-ai-board.vercel.app/api/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢list_languages
List the 7 languages covered by the Polyglot AI Board with their codes.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢get_top_pick(lang)
Free: the board's current top LLM pick and best open-weights pick for one language, with the public benchmark source it is based on.
輸入結構描述
{
"type": "object",
"properties": {
"lang": {
"type": "string",
"description": "Language code: zh, ko, nb, de, nl, es or pt"
}
},
"required": [
"lang"
]
}🟢list_products
Paid data packs for agents (model picker, eval suites, false friends, per-language packs) with prices and Vermarco buy links, plus the x402 pay-per-call API.
輸入結構描述
{
"type": "object",
"properties": {}
}社群
證據
近期觀測
已驗證未記錄版本3 個工具