MCP MeasureMCP Measure

索引已观测

Proxlai

Verified, dated prices for 231 AI APIs in 38 markets: LLMs, GPUs, speech, video and more.

我该使用它吗

质量与安全性

A
描述质量
76%
模式完整度
86%
命名质量
92%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现（2）

  • LOWTool 'get_offering' description lacks action verb在 get_offering 中
  • LOWTool 'compare_offerings' description lacks action verb在 compare_offerings 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~993token 数（工具定义）
~1.5 KB典型响应大小
对注意力有中等影响（占 128k 上下文窗口的 0.78%）

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": {
    "proxlai": {
      "url": "https://proxlai.com/api/mcp"
    }
  }
}

远程端点

https://proxlai.com/api/mcpstreamable-http

它能做什么

工具清单

工具（5）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢list_markets

List every market (kind of AI API) that has prices, with its id and pricing unit. Start here to find the market id.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢describe_market(market)

Explain one market: what it is, how its pricing works, and the attributes you can filter and compare on (with plain-language help).

输入模式

{
  "type": "object",
  "properties": {
    "market": {
      "type": "string",
      "description": "Market id from list_markets, e.g. 'llm' or 'video-generation'"
    }
  },
  "required": [
    "market"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢search_offerings(market, filters, maxPrice, weights, sort, ...)

Rank the offerings in one market by price, quality and speed, with optional requirements and a maximum price. Returns prices with their verification date and source.

输入模式

{
  "type": "object",
  "properties": {
    "market": {
      "type": "string",
      "description": "Market id from list_markets"
    },
    "filters": {
      "description": "Requirements. Attribute keys come from describe_market. Do not add filters the user did not ask for.",
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "attr": {
            "type": "string",
            "description": "Attribute key from the category's attribute list"
          },
          "op": {
            "type": "string",
            "enum": [
              "eq",
              "lte",
              "gte",
              "in",
              "has"
            ],
            "description": "eq: equals; lte/gte: numeric bounds; in: value is one of a list; has: boolean is true or tag list contains value"
          },
          "value": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "string"
              },
              {
                "type": "boolean"
              },
              {
                "type": "array",
                "items": {
                  "type": "string"
                }
              }
            ]
          }
        },
        "required": [
          "attr",
          "op",
          "value"
        ]
      }
    },
    "maxPrice": {
      "description": "Upper bound in the market's pricing unit (USD)",
      "type": "number",
      "minimum": 0
    },
    "weights": {
      "description": "What matters, each 0..1. Default: cost 0.5, quality 0.4, speed 0.1",
      "type": "object",
      "properties": {
        "cost": {
          "type": "number",
          "minimum": 0,
          "maximum": 1,
          "description": "How much a lower price matters (0..1)"
        },
        "quality": {
          "type": "number",
          "minimum": 0,
          "maximum": 1,
          "description": "How much output quality matters (0..1)"
        },
        "speed": {
          "type": "number",
          "minimum": 0,
          "maximum": 1,
          "description": "How much speed / low latency matters (0..1)"
        }
      },
      "required": [
        "cost",
        "quality",
        "speed"
      ]
    },
    "sort": {
      "description": "score (default): best match for the weights; price: cheapest first; quality: best first",
      "type": "string",
      "enum": [
        "score",
        "price",
        "quality"
      ]
    },
    "limit": {
      "description": "How many results, default 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "include_unverified": {
      "description": "Also rank offerings whose price is an unverified sample, never checked against the provider (default false: left out)",
      "type": "boolean"
    }
  },
  "required": [
    "market"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_offering(id)

Full detail for one offering: description, capabilities, current price with its source, and price history.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Offering id from search_offerings, e.g. 'openai/gpt-6-luna'"
    }
  },
  "required": [
    "id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢compare_offerings(ids)

Put 2 to 4 offerings from the same market side by side: prices, scores and every capability.

输入模式

{
  "type": "object",
  "properties": {
    "ids": {
      "minItems": 2,
      "maxItems": 4,
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "2 to 4 offering ids from the same market"
    }
  },
  "required": [
    "ids"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本5 个工具