MCP MeasureMCP Measure

index observed

AI 模型下架與替代日程

OpenAI、Claude、Gemini 模型下架日、剩餘天數與官方建議替代，可檢查程式碼裡的模型。每筆附官方來源。

Should I use this

Quality & Safety

B
Description quality
58%
Schema completeness
78%
Naming quality
90%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (5)

  • LOWTool 'upcoming_ai_model_shutdowns' description lacks action verbin upcoming_ai_model_shutdowns
  • LOWTool 'find_ai_model_replacement' description lacks action verbin find_ai_model_replacement
  • LOWTool 'ai_model_shutdown_calendar' description lacks action verbin ai_model_shutdown_calendar
  • LOWTool 'check_code_for_deprecated_models' description lacks action verbin check_code_for_deprecated_models
  • LOWTool 'check_code_for_deprecated_models' name length outside 3-30 rangein check_code_for_deprecated_models

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~565Tokens (tool definitions)
~354 BTypical response size
Minimal attention impact (0.44% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "models": {
      "url": "https://models.penguindriver.com/mcp"
    }
  }
}

Remote endpoints

https://models.penguindriver.com/mcpstreamable-http

What it can do

Tool inventory

Tools (6)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢list_ai_models(provider, status, kind)

列出 OpenAI、Anthropic（Claude）、Google（Gemini）模型與 API 功能的淘汰狀態、下架日與官方建議替代；可依公司、狀態、類型篩選。

Input Schema

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "enum": [
        "openai",
        "anthropic",
        "google"
      ]
    },
    "status": {
      "type": "string",
      "enum": [
        "scheduled",
        "deprecated",
        "active",
        "retired"
      ]
    },
    "kind": {
      "type": "string",
      "enum": [
        "chat",
        "reasoning",
        "image",
        "video",
        "audio",
        "realtime",
        "transcribe",
        "tts",
        "embedding",
        "music",
        "robotics",
        "agent",
        "platform",
        "finetune"
      ]
    }
  }
}
🟢get_ai_model(id)

查單一模型 ID（如 gpt-4o-2024-05-13、claude-3-5-haiku-20241022、gemini-2.0-flash）的狀態、宣布淘汰日、下架日、剩幾天、官方建議替代與來源。

Input Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ]
}
⚪upcoming_ai_model_shutdowns(days)

列出幾天內將下架的 AI 模型（預設 90 天），依下架日排序。

Input Schema

{
  "type": "object",
  "properties": {
    "days": {
      "type": "number"
    }
  }
}
🟢find_ai_model_replacement(q)

查某個模型官方建議改用哪個模型。

Input Schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string"
    }
  },
  "required": [
    "q"
  ]
}
⚪ai_model_shutdown_calendar(month)

依月份列出模型下架日。

Input Schema

{
  "type": "object",
  "properties": {
    "month": {
      "type": "string",
      "description": "YYYY-MM"
    }
  }
}
🟢check_code_for_deprecated_models(text)

貼上程式碼、設定檔或模型 ID 清單，找出已下架或即將下架的模型（最多 10 個）。

Input Schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    }
  },
  "required": [
    "text"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded6 tools