AI Model Lifecycle Index is an MCP server with 4 tools an agent can call, among them get_model_lifecycle_all, is_model_live, model_lifecycle. It answers at https://lifecycle.oscar-lopez.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 6 November 2026, succeeded.
Cross-vendor AI model lifecycle: status, sunset dates, and migration targets, source-cited.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_model_lifecycle_all | Full cross-vendor lifecycle export (all tracked models). Free during the public preview; metered via x402 when live. Inputs: provider |
is_model_live | 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. Inputs: model_id |
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. Inputs: model_id |
upcoming_deprecations | FREE. AI models being shut down within the next N days across OpenAI, Anthropic, Google, and Amazon Bedrock, with migration targets. Default 90 days. Inputs: within_days |
Every block below points at https://lifecycle.oscar-lopez.com/mcp. Pick your client and copy.
claude mcp add --transport http ai-model-lifecycle-index https://lifecycle.oscar-lopez.com/mcp
{
"mcpServers": {
"ai-model-lifecycle-index": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://lifecycle.oscar-lopez.com/mcp"]
}
}
}{
"mcpServers": {
"ai-model-lifecycle-index": {
"url": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}{
"servers": {
"ai-model-lifecycle-index": {
"type": "http",
"url": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}{
"context_servers": {
"ai-model-lifecycle-index": {
"url": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}{
"mcpServers": {
"ai-model-lifecycle-index": {
"serverUrl": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}{
"mcpServers": {
"ai-model-lifecycle-index": {
"url": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}name: AI Model Lifecycle Index
version: 0.0.1
schema: v1
mcpServers:
- name: AI Model Lifecycle Index
type: streamable-http
url: https://lifecycle.oscar-lopez.com/mcp{
"mcpServers": {
"ai-model-lifecycle-index": {
"httpUrl": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}{
"mcpServers": {
"ai-model-lifecycle-index": {
"type": "http",
"url": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}{
"mcpServers": {
"ai-model-lifecycle-index": {
"url": "https://lifecycle.oscar-lopez.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Flifecycle.oscar-lopez.com%2Fmcp&type=streamable_http&id=ai-model-lifecycle-index&name=AI%20Model%20Lifecycle%20Index
It answered our last check on 6 November 2026 in 144 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
4, as returned by the server's own tools/list on 11 November 2026: get_model_lifecycle_all, is_model_live, model_lifecycle, upcoming_deprecations.
It answered our last check on 6 November 2026 in 144 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://lifecycle.oscar-lopez.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.oscarlopez-gif. Endpoint host: lifecycle.oscar-lopez.com. ARD identifier: urn:air:io.github.oscarlopez-gif:mcp:ai-model-lifecycle-index.
First indexed 19 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.