Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
Remote server: your requests and data go to aideprecations--89b1777ed29f11f1a12e1607ee4eb77e.web.val.run. Claude Code: claude mcp add --transport http ai-deprecations https://aideprecations--89b1777ed29f11f1a12e1607ee4eb77e.web.val.run/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
get_shutdown_date — Get the official deprecation/shutdown date, replacement and source for an AI model ID (e.g. gpt-4o-2024-08-06, claude-sonnet-4-5).list_upcoming — List AI model shutdowns in the next N days, soonest first.search_models — Search all tracked AI models (including retired) by name.get_provider — All tracked models for one provider (openai, anthropic, google-gemini, google-vertex, azure-openai, aws-bedrock, mistral, cohere).get_changes_since — List tracked AI model records whose status, deprecation/shutdown date, replacement or source changed since an ISO 8601 time. Poll this to stsubscribe_alerts — Subscribe to deprecation/shutdown change alerts. Give a public https webhook URL (JSON POST on every change, checked daily) or an email (douunsubscribe — Stop webhook alerts using the token from subscribe_alerts. Email subscribers unsubscribe from the link in any email.get_coverage — Per-provider coverage today: rows with a known shutdown date, rows where the vendor page gives no date, rows not verified today, and officiaNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.