modelright
Live registry of AI model specs, context windows, and per-token pricing.
我该使用它吗
质量与安全性
发现（1）
- LOWTool 'compare_models' description lacks action verb在 compare_models 中
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": {
"modelright": {
"url": "https://modelright.dev/api/mcp"
}
}
}远程端点
https://modelright.dev/api/mcpstreamable-http它能做什么
工具清单
工具（6）
🟢list_providers
List providers tracked by the registry with their model counts. Use provider slugs in list_models / get_model / compare_models.
输入模式
{
"type": "object",
"properties": {}
}🟢search_models(q, limit)
Substring search across model name, slug, and provider — the fast path to a model's provider/slug pair for the detail tools.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "Search text, e.g. 'sonnet'"
},
"limit": {
"description": "Max results (default 20)",
"type": "integer",
"minimum": 1,
"maximum": 100
}
},
"required": [
"q"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_models(provider, modality, status, minContextWindow, maxInputPricePerM, ...)
List tracked models with pricing and context windows. Filter by provider, modality tag, status, or price/context bounds.
输入模式
{
"type": "object",
"properties": {
"provider": {
"description": "Provider slug filter, e.g. 'anthropic'",
"type": "string"
},
"modality": {
"description": "Modality tag filter, e.g. 'text', 'image', 'audio'",
"type": "string"
},
"status": {
"description": "Status filter, e.g. 'available', 'deprecated'",
"type": "string"
},
"minContextWindow": {
"description": "Minimum context window",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"maxInputPricePerM": {
"description": "Max input price per 1M tokens (USD)",
"type": "number",
"minimum": 0
},
"sort": {
"description": "Sort order (default name)",
"type": "string",
"enum": [
"name",
"input_price_asc",
"input_price_desc",
"context_desc"
]
},
"limit": {
"description": "Max results (default 100)",
"type": "integer",
"minimum": 1,
"maximum": 500
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_model(provider, slug, snapshots)
Full detail for one model (provider+slug from search_models): specs, current price, status, and recent price/availability snapshots.
输入模式
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"minLength": 1,
"description": "Provider slug, e.g. 'openai'"
},
"slug": {
"type": "string",
"minLength": 1,
"description": "Model slug, e.g. 'gpt-4o'"
},
"snapshots": {
"description": "Recent snapshots to include (default 10, 0 to skip)",
"type": "integer",
"minimum": 0,
"maximum": 50
}
},
"required": [
"provider",
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}⚪compare_models(models)
Side-by-side comparison of 2-10 models by provider/slug: context window, input/output price per 1M tokens, modalities, status.
输入模式
{
"type": "object",
"properties": {
"models": {
"minItems": 2,
"maxItems": 10,
"type": "array",
"items": {
"type": "object",
"properties": {
"provider": {
"type": "string",
"minLength": 1,
"description": "Provider slug, e.g. 'openai'"
},
"slug": {
"type": "string",
"minLength": 1,
"description": "Model slug, e.g. 'gpt-4o'"
}
},
"required": [
"provider",
"slug"
]
},
"description": "Models to compare"
}
},
"required": [
"models"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_ingest_status(limit)
Data-freshness check: registry totals and the most recent ingest runs (source, model count, status, time).
输入模式
{
"type": "object",
"properties": {
"limit": {
"description": "Recent ingest runs to return (default 10)",
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社区
证据