Skip to content

LLMIntel Model Lifecycle

by llmintel.ai · remote · local (npm) · no sign-in to list tools · v0.2.0 · published by ai.llmintel

Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.

Changes · 3
CompareRegistry entry

5 tools: 3 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http model-lifecycle https://llmintel.ai/v1/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 3Claude Code: ask
  • check_modelCheck whether an LLM model id is safe to use, deprecated, or retired, and what to migrate to.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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 changing any hardcoded model id.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • recent_lifecycle_changesLifecycle state changes across all tracked providers, newest first.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Lifecycle state changes across all tracked providers, newest first. Use this to answer 'what model deprecations happened recently?'.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • suggest_replacementGiven 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 2Claude Code: allow
  • list_retiring_modelsList tracked models scheduled to retire within a time window, soonest first.No findings

    Why it is in this group

    • The name "list_retiring_models" says "list": a word for reading.
    Description, as the server wrote it
    List tracked models scheduled to retire within a time window, soonest first. Use this to audit a codebase or plan migration work.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • search_modelsList tracked models, optionally filtered by provider and lifecycle state.No findings

    Why it is in this group

    • The name "search_models" says "search": a word for reading.
    Description, as the server wrote it
    List tracked models, optionally filtered by provider and lifecycle state. Use this to discover what is currently available from a provider.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http model-lifecycle https://llmintel.ai/v1/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__model-lifecycle__list_retiring_models",
      "mcp__model-lifecycle__search_models"
    ],
    "ask": [
      "mcp__model-lifecycle__check_model",
      "mcp__model-lifecycle__suggest_replacement",
      "mcp__model-lifecycle__recent_lifecycle_changes"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as model-lifecycle. Review it before you use it.