# Llmintel Model Lifecycle MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.llmintel%2Fmodel-lifecycle
Registry id: `mcp-registry/ai.llmintel/model-lifecycle`
Status: live (checked 2026-10-26T22:31:43.622Z)

## Verdict

Llmintel Model Lifecycle MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 416 ms median handshake and 8 outages in 90 days. Its agent-readiness grade is A (95/100) across 5 tools, costing an agent about 849 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 416 ms | 55% of MCP servers |
| p95 handshake latency | 2350 ms | — |
| Checks in 30 days | 4,932 | — |
| Outages, 90 days | 8 | — |
| Median recovery | 3 min | — |
| Agent-readiness score | 95/100 (A) | 80% of MCP servers |
| Tools | 5 | — |
| Tool-list size for an agent | ~849 tokens | 77% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "llmintel-model-lifecycle-mcp-server": {
      "type": "http",
      "url": "https://llmintel.ai/v1/mcp"
    }
  }
}
```

Claude Code:

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

## Tools (5)

- `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-sonn
- `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.
- `recent_lifecycle_changes`: Lifecycle state changes across all tracked providers, newest first. Use this to answer 'what model deprecations happened recently?'.
- `search_models`: List tracked models, optionally filtered by provider and lifecycle state. Use this to discover what is currently available from a provider.
- `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 cons

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.