# LLMIntel Model Lifecycle MCP server

> Lets an AI agent check if LLM model IDs are deprecated or retired and find recommended replacements across major providers.

- Repository: https://github.com/hivemindunit/llmintel-mcp
- Page: https://hostedmcp.org/servers/hivemindunit/model-lifecycle
- Transport: stdio, remote
- Stars: 1
- License: MIT
- Latest version: 0.2.0

## Install

### Claude Code

```sh
claude mcp add --env 'LLMINTEL_API_KEY=<YOUR_LLMINTEL_API_KEY>' model-lifecycle -- npx -y @llmintel/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "model-lifecycle": {
      "command": "npx",
      "args": [
        "-y",
        "@llmintel/mcp"
      ],
      "env": {
        "LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "model-lifecycle": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@llmintel/mcp"
      ],
      "env": {
        "LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"model-lifecycle","type":"stdio","command":"npx","args":["-y","@llmintel/mcp"],"env":{"LLMINTEL_API_KEY":"<YOUR_LLMINTEL_API_KEY>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "model-lifecycle": {
      "command": "npx",
      "args": [
        "-y",
        "@llmintel/mcp"
      ],
      "env": {
        "LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add model-lifecycle --env 'LLMINTEL_API_KEY=<YOUR_LLMINTEL_API_KEY>' -- npx -y @llmintel/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.model-lifecycle]
command = "npx"
args = ["-y", "@llmintel/mcp"]

[mcp_servers.model-lifecycle.env]
LLMINTEL_API_KEY = "<YOUR_LLMINTEL_API_KEY>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'LLMINTEL_API_KEY=<YOUR_LLMINTEL_API_KEY>' model-lifecycle npx -- -y @llmintel/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "model-lifecycle": {
      "command": "npx",
      "args": [
        "-y",
        "@llmintel/mcp"
      ],
      "env": {
        "LLMINTEL_API_KEY": "<YOUR_LLMINTEL_API_KEY>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `LLMINTEL_API_KEY` | no | yes | Optional. The catalog is public and needs no key; supplying one only raises the rate-limit budget. |
| `LLMINTEL_BASE_URL` | no | no | Optional. Override the catalog origin (defaults to https://llmintel.ai). Useful for self-hosted or staging deployments. |

## Tools (5)

- `check_model`
- `list_retiring_models`
- `suggest_replacement`
- `search_models`
- `recent_lifecycle_changes`

## FAQ

### Do I need an API key to use this server?

No, the catalog is public and you can use it without an API key or signup.

### What happens if a model is not in the catalog?

The server will return a message stating the model is not in the catalog and to verify it with the provider, rather than assuming it is safe.

### Can I use this without installing an npm package?

Yes, you can use a hosted HTTP endpoint if your MCP host supports URLs.

### Is there a rate limit for anonymous users?

Yes, anonymous callers are limited to 30 requests per minute per IP.
