isitdeprecated
Check if an AI model is deprecated, retiring, or silently changed price or context window.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
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": {
"isitdeprecated": {
"url": "https://isitdeprecated.com/mcp"
}
}
}遠端端點
https://isitdeprecated.com/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢check_model(model)
Check whether an AI model identifier is deprecated, retiring, or has silently changed (price, context window, capabilities). Accepts any spelling a provider or SDK uses, e.g. 'gpt-4-turbo', 'azure/gpt-4.1-mini', 'claude-opus-4-1-20250805'. Call this before writing a model identifier into code.
輸入結構描述
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model identifier to check"
}
},
"required": [
"model"
]
}🟢check_models(models)
Check many model identifiers at once and report which are retired or scheduled for retirement. Use when auditing a codebase or config.
輸入結構描述
{
"type": "object",
"properties": {
"models": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 100 identifiers"
}
},
"required": [
"models"
]
}🟢upcoming_retirements(within_days)
List models with an announced retirement date inside a horizon, soonest first.
輸入結構描述
{
"type": "object",
"properties": {
"within_days": {
"type": "integer",
"default": 90
}
}
}⚪recent_changes(limit, min_severity)
Recent breaking changes across AI model APIs: price moves, context-window cuts, removed capabilities, removals. One entry per real upstream change.
輸入結構描述
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 30
},
"min_severity": {
"type": "string",
"enum": [
"critical",
"high",
"medium",
"low",
"info"
],
"default": "medium"
}
}
}社群
證據