Hello, AI
Ask your assistant which frontier model to use and get a live, Elo-backed answer.
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": {
"directory": {
"url": "https://helloai.com/mcp"
}
}
}远程端点
https://helloai.com/mcpstreamable-http它能做什么
工具清单
工具（6）
🟢recommend_models(task, max_cost, min_context, provider, limit)
Rank Hello, AI's tracked frontier models for a task. Same scoring as GET /api/recommend: task match 40%, Elo 35%, input cost 15%, context 10% (Elo 55%, cost 25%, context 20% when no task matches). Only rated models rank; unrated ones are listed separately. score is an ordering aid, not a quality measure.
输入模式
{
"type": "object",
"properties": {
"task": {
"type": "string",
"maxLength": 64,
"description": "Use case, matched against the category names: Overall Preference, Coding & Engineering, Hard Reasoning & Science, Honest Daily Use. Examples: coding, reasoning, overall, daily."
},
"max_cost": {
"type": "number",
"exclusiveMinimum": 0,
"description": "Maximum USD per 1 million input tokens; models above it are excluded."
},
"min_context": {
"type": "integer",
"minimum": 1,
"description": "Minimum context window in tokens; models below it are excluded."
},
"provider": {
"type": "string",
"description": "Provider name, case-insensitive exact match (for example Anthropic, Google, xAI)."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"default": 3,
"description": "How many ranked rows to return, 1 to 10. Default 3."
}
},
"additionalProperties": false
}🟢list_models(provider)
All tracked models with full records: Elo and its provenance (elo_source), prices per million tokens, context window, strengths, description. rated is false when the stored Elo is a predecessor's, missing or stale.
输入模式
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "Provider name, case-insensitive substring match."
}
},
"additionalProperties": false
}🟢get_model(id)
One tracked model's full record by id (claude, fable, muse, gemini, qwen, grok) or exact name.
输入模式
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Model id or exact name"
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢list_categories
The curated use-case categories with their curator-chosen leader and a one-paragraph insight. The leader is a hand-set label, not derived from Elo.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢list_articles(limit)
Recent Hello, AI articles, newest first: title, date, category, excerpt and URL.
输入模式
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10,
"description": "Articles to return, 1 to 50. Default 10."
}
},
"additionalProperties": false
}🟢get_status
Data freshness, app version, model and article counts, the scoring version and snapshot fingerprint, and the rate limit.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}社区
证据