MCP MeasureMCP Measure

索引已觀測

LLM Provider Intelligence

LLM provider intelligence: recommendations, pricing, and status

我該用這個嗎

品質與安全性

A
說明品質
93%
結構描述完整度
90%
命名品質
93%
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

~351Token（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 0.27%）

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": {
    "intel": {
      "url": "https://intel.memoryapi.org/mcp"
    }
  }
}

遠端端點

https://intel.memoryapi.org/mcpstreamable-http

它能做什麼

工具清單

工具（3）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢recommend_llm(task, priority, require_tool_calling, min_context, max_price_per_million)

Get the best LLM provider for your specific agent task. Returns top 3 ranked recommendations with reasoning.

輸入結構描述

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task type: tool_calling, reasoning, rag, summarization, high_volume, low_latency, general",
      "default": "general"
    },
    "priority": {
      "type": "string",
      "description": "Optimize for: balanced, cost, speed, quality",
      "default": "balanced"
    },
    "require_tool_calling": {
      "type": "boolean",
      "description": "Only return providers with tool calling support"
    },
    "min_context": {
      "type": "number",
      "description": "Minimum context window needed in tokens"
    },
    "max_price_per_million": {
      "type": "number",
      "description": "Maximum input price per million tokens (USD)"
    }
  }
}
🟢list_providers(tool_calling, x402_native, max_price, best_for)

List LLM providers with their capabilities, pricing, and agent scores. Filter by specific requirements.

輸入結構描述

{
  "type": "object",
  "properties": {
    "tool_calling": {
      "type": "boolean",
      "description": "Only show providers with tool calling"
    },
    "x402_native": {
      "type": "boolean",
      "description": "Only show x402-native providers"
    },
    "max_price": {
      "type": "number",
      "description": "Max input price per million tokens"
    },
    "best_for": {
      "type": "string",
      "description": "Filter by use case: tool_calling, reasoning, cost, speed, long_context, rag"
    }
  }
}
🟢check_provider_status(provider)

Check operational status and recent latency for one or all LLM providers.

輸入結構描述

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "description": "Specific provider slug (e.g. openai-gpt4o). Omit for all."
    }
  }
}

建議的提示詞

list_items
List all [items] available in LLM Provider Intelligence
預期的工具： list_providers
browse_collection
Show me the [collection] from LLM Provider Intelligence
預期的工具： list_providers

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本3 個工具
已驗證未記錄版本3 個工具