model_lifecycle
FREE. Lifecycle of one AI model: status (active/preview/deprecated/retired), release/deprecation/shutdown dates, days until shutdown, recommended migration target, and the official source URL.
model_id必填
io.github.oscarlopez-gif由 GitHub 帳號 oscarlopez-gif 發布v0.1.0更新於 Oct 24, 2026
Cross-vendor AI model lifecycle: status, sunset dates, and migration targets, source-cited.
一個遠端 MCP 伺服器,讓助理查詢 OpenAI、Anthropic、Google 與 Amazon Bedrock 上的 AI 模型是否仍可用、何時下線,以及建議遷移到哪個模型。
Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.oscarlopez-gif%2Fai-model-lifecycle-index/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"ai-model-lifecycle-index": {
"type": "http",
"url": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}A source-cited, cross-vendor record of AI model lifecycle — is a model still live, when does it sunset, and what's the migration target — across OpenAI, Anthropic, Google (Gemini), and Amazon Bedrock. Every date is transcribed from the provider's own official deprecation/lifecycle page and carries that source URL. Built for agents that need to know, at runtime, whether the model they're about to call still exists.
71 models across 4 providers (active / preview / deprecated / retired), with status, release / deprecation / shutdown dates, and provider-recommended replacements. Verified 2026-09-08.
GET /v1/lifecycle/model?id=ID — one model: status, dates, days-to-shutdown, replacement, sourceGET /v1/lifecycle/deprecations?within_days=90 — models shutting down within N daysGET /v1/lifecycle/provider?provider=openai|anthropic|google|aws-bedrock — a provider's modelsGET /v1/lifecycle/stats — counts by provider/status + next shutdownGET /v1/lifecycle/all — full export (free during the public preview; metered via x402 when live)Endpoint: https://lifecycle.oscar-lopez.com/mcp
model_lifecycle — full lifecycle of one model (free)is_model_live — is a model still callable, with its sunset date (free)upcoming_deprecations — models sunsetting within N days across all providers (free)get_model_lifecycle_all — full export (free during preview)/.well-known/agent-card.json (A2A), /.well-known/x402, /openapi.json
Cloudflare Worker + D1. The index is derived live from a models table; days-until-shutdown is
computed at request time. Values come from official provider pages only; fields a provider doesn't
publish are left blank rather than inferred. A model's lifecycle on a hosting platform (e.g. Amazon
Bedrock) can differ from the model-maker's own API — each row records which surface it describes.
來源:README.md,提交 ea63349
FREE. Lifecycle of one AI model: status (active/preview/deprecated/retired), release/deprecation/shutdown dates, days until shutdown, recommended migration target, and the official source URL.
model_id必填FREE. Fast check of whether an AI model is still callable, plus its sunset date and days remaining. Use before depending on a model at runtime.
model_id必填FREE. AI models being shut down within the next N days across OpenAI, Anthropic, Google, and Amazon Bedrock, with migration targets. Default 90 days.
within_daysFull cross-vendor lifecycle export (all tracked models). Free during the public preview; metered via x402 when live.
provider已滿足適用檢查項的 90%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
請在儲存庫或註冊中心條目中宣告授權條款。

tools.model官方發布者
零認證遠端工具伺服器,讓代理程式讀取一次性信箱驗證碼、保存檢查點、接收 Webhook、排定喚醒、取得任務回執,並把網頁轉成 Markdown。
ai.com.nlp官方發布者
搜尋精選的開放權重AI模型發布、授權條款、架構和原始來源。AI 翻譯

foundation.uor.hub官方發布者
一個遠端 MCP 伺服器,讓助理搜尋開放模型索引,並取得附有 SHA-256 校驗值的下載連結。

由 GitHub 帳號 Greatbeing 發布
探測相容於 OpenAI 的模型閘道,依實測延遲與成功率為模型排名,並推薦該用哪個模型。

由 GitHub 帳號 Sagargupta16 發布
本機 MCP 伺服器,把 AWS Bedrock 的文字、影像、影片與嵌入模型包裝成九個工具,讓助理可以提問、比較與評審模型。