LLMIntel Model Lifecycle
Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"model-lifecycle": {
"command": "npx",
"args": [
"@llmintel/mcp"
]
}
}
}可运行的软件包
0.2.0stdio远程端点
https://llmintel.ai/v1/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢check_model(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 changing any hardcoded model id.
输入模式
{
"type": "object",
"properties": {
"model": {
"type": "string",
"minLength": 1,
"description": "Model id or alias exactly as it appears in code, e.g. 'gpt-4o'."
}
},
"required": [
"model"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_retiring_models(withinDays, provider)
List tracked models scheduled to retire within a time window, soonest first. Use this to audit a codebase or plan migration work.
输入模式
{
"type": "object",
"properties": {
"withinDays": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 1095,
"default": 180,
"description": "Only include models retiring within this many days. Defaults to 180."
},
"provider": {
"type": "string",
"enum": [
"openai",
"anthropic",
"azure",
"bedrock",
"google",
"cohere",
"mistral"
],
"description": "Restrict to one provider. Omit for all providers."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢suggest_replacement(model)
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.
输入模式
{
"type": "object",
"properties": {
"model": {
"type": "string",
"minLength": 1,
"description": "Model id or alias to find a replacement for."
}
},
"required": [
"model"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_models(provider, state, limit)
List tracked models, optionally filtered by provider and lifecycle state. Use this to discover what is currently available from a provider.
输入模式
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"enum": [
"openai",
"anthropic",
"azure",
"bedrock",
"google",
"cohere",
"mistral"
],
"description": "Filter by provider."
},
"state": {
"type": "string",
"enum": [
"announced",
"active",
"legacy",
"deprecated",
"retiring",
"retired"
],
"description": "Filter by canonical lifecycle state, e.g. 'active' or 'deprecated'."
},
"limit": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 200,
"default": 50,
"description": "Maximum results."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢recent_lifecycle_changes(sinceDays, provider)
Lifecycle state changes across all tracked providers, newest first. Use this to answer 'what model deprecations happened recently?'.
输入模式
{
"type": "object",
"properties": {
"sinceDays": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 365,
"default": 30,
"description": "Look back this many days. Defaults to 30."
},
"provider": {
"type": "string",
"enum": [
"openai",
"anthropic",
"azure",
"bedrock",
"google",
"cohere",
"mistral"
],
"description": "Restrict to one provider."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据