MCP MeasureMCP Measure

索引已觀測

ai-cost-optimizer

Cloudflare Workers MCP server: ai-cost-optimizer

我該用這個嗎

品質與安全性

A
說明品質
96%
結構描述完整度
96%
命名品質
80%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~584Token（工具定義）
~1.1 KB典型回應大小
極小的注意力影響（128k 上下文的 0.46%）

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案：

{
  "mcpServers": {
    "ai-cost-optimizer": {
      "url": "https://api.lazy-mac.com/ai-cost-optimizer/mcp"
    }
  }
}

遠端端點

https://api.lazy-mac.com/ai-cost-optimizer/mcpstreamable-http

它能做什麼

工具清單

工具（5）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢cost_tracker(action, model, inputTokens, outputTokens, team, ...)

Record and retrieve AI API call costs by team. Persists to Cloudflare KV — survives cold starts and scale-out.

輸入結構描述

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "record",
        "get"
      ],
      "description": "\"record\" to log a call, \"get\" to retrieve recent records"
    },
    "model": {
      "type": "string",
      "description": "Model ID (e.g., claude-3-5-sonnet-20241022, gpt-4o, gemini-2.0-flash)"
    },
    "inputTokens": {
      "type": "number",
      "description": "Number of input/prompt tokens consumed"
    },
    "outputTokens": {
      "type": "number",
      "description": "Number of output/completion tokens generated"
    },
    "team": {
      "type": "string",
      "description": "Team or project identifier (default: \"default\")"
    },
    "metadata": {
      "type": "object",
      "description": "Optional key-value metadata (request ID, user, feature flag, etc.)"
    }
  },
  "required": [
    "action"
  ]
}
🟢token_calculator(model, inputTokens, outputTokens)

Calculate cost from token counts for any supported AI model. Stateless — no KV required.

輸入結構描述

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model ID to price"
    },
    "inputTokens": {
      "type": "number",
      "description": "Input token count"
    },
    "outputTokens": {
      "type": "number",
      "description": "Output token count"
    }
  },
  "required": [
    "model",
    "inputTokens",
    "outputTokens"
  ]
}
🟡budget_alert(action, team, budgetLimit, threshold)

Set and check budget limits for teams. Raises a flag when a configurable spending threshold is reached.

輸入結構描述

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "set",
        "check"
      ],
      "description": "\"set\" to configure a budget, \"check\" to get current status"
    },
    "team": {
      "type": "string",
      "description": "Team identifier"
    },
    "budgetLimit": {
      "type": "number",
      "description": "USD budget cap"
    },
    "threshold": {
      "type": "number",
      "description": "Alert threshold percentage 0–100 (default: 80)"
    }
  },
  "required": [
    "action"
  ]
}
🟢model_breakdown(team, days)

Analyze costs broken down by model for a given team over a configurable time window.

輸入結構描述

{
  "type": "object",
  "properties": {
    "team": {
      "type": "string",
      "description": "Team identifier"
    },
    "days": {
      "type": "number",
      "description": "Lookback window in days (default: 30)"
    }
  }
}
⚪cost_forecast(team, forecastDays, historicalDays)

Forecast future AI spend based on historical usage patterns using daily-average linear projection.

輸入結構描述

{
  "type": "object",
  "properties": {
    "team": {
      "type": "string",
      "description": "Team identifier"
    },
    "forecastDays": {
      "type": "number",
      "description": "Days to project ahead (default: 7)"
    },
    "historicalDays": {
      "type": "number",
      "description": "Days of history to base the forecast on (default: 30)"
    }
  }
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本5 個工具
已驗證未記錄版本5 個工具
已驗證未記錄版本5 個工具