LLMIntel Model Lifecycle is a remote MCP server that gives an AI agent 5 tools, among them check_model, list_retiring_models, recent_lifecycle_changes. It answers at https://llmintel.ai/v1/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 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_model | Check whether an LLM model id is safe to use, deprecated, or retired, and what to migrate to. Accepts the exact string used in code (e.g. 'gpt-4o', 'claude-sonnet-4-5-20250929', 'anthropic/claude-opus-4-1'). Call this before writing or chan Inputs: model |
list_retiring_models | List tracked models scheduled to retire within a time window, soonest first. Use this to audit a codebase or plan migration work. Inputs: withinDays, provider |
recent_lifecycle_changes | Lifecycle state changes across all tracked providers, newest first. Use this to answer 'what model deprecations happened recently?'. Inputs: sinceDays, provider |
search_models | List tracked models, optionally filtered by provider and lifecycle state. Use this to discover what is currently available from a provider. Inputs: provider, state, limit |
suggest_replacement | Given a deprecated or retiring model, return the provider's recommended replacement(s) and, when none is published, active models from the same provider to consider. Inputs: model |
Every block below points at https://llmintel.ai/v1/mcp. Pick your client and copy.
claude mcp add --transport http llmintel-model-lifecycle https://llmintel.ai/v1/mcp
{
"mcpServers": {
"llmintel-model-lifecycle": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://llmintel.ai/v1/mcp"]
}
}
}{
"mcpServers": {
"llmintel-model-lifecycle": {
"url": "https://llmintel.ai/v1/mcp"
}
}
}{
"servers": {
"llmintel-model-lifecycle": {
"type": "http",
"url": "https://llmintel.ai/v1/mcp"
}
}
}{
"context_servers": {
"llmintel-model-lifecycle": {
"url": "https://llmintel.ai/v1/mcp"
}
}
}{
"mcpServers": {
"llmintel-model-lifecycle": {
"serverUrl": "https://llmintel.ai/v1/mcp"
}
}
}{
"mcpServers": {
"llmintel-model-lifecycle": {
"url": "https://llmintel.ai/v1/mcp"
}
}
}name: LLMIntel Model Lifecycle
version: 0.0.1
schema: v1
mcpServers:
- name: LLMIntel Model Lifecycle
type: streamable-http
url: https://llmintel.ai/v1/mcp{
"mcpServers": {
"llmintel-model-lifecycle": {
"httpUrl": "https://llmintel.ai/v1/mcp"
}
}
}{
"mcpServers": {
"llmintel-model-lifecycle": {
"type": "http",
"url": "https://llmintel.ai/v1/mcp"
}
}
}{
"mcpServers": {
"llmintel-model-lifecycle": {
"url": "https://llmintel.ai/v1/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fllmintel.ai%2Fv1%2Fmcp&type=streamable_http&id=llmintel-model-lifecycle&name=LLMIntel%20Model%20Lifecycle
It answered our last check on 17 October 2026 in 188 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by llmintel.ai and served from llmintel.ai, the vendor's own domain: https://llmintel.ai/v1/mcp.
5, as returned by the server's own tools/list on 8 September 2026: check_model, list_retiring_models, recent_lifecycle_changes, search_models, suggest_replacement.
It answered our last check on 17 October 2026 in 188 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://llmintel.ai/v1/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: ai.llmintel. Endpoint host: llmintel.ai. ARD identifier: urn:air:ai.llmintel:mcp:model-lifecycle.
First indexed 31 August 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.