MCP MeasureMCP Measure

索引已觀測

embedding-search

Cloudflare Workers MCP server: embedding-search

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

~293Token（工具定義）
~747 B典型回應大小
極小的注意力影響（128k 上下文的 0.23%）

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": {
    "embedding-search": {
      "url": "https://api.lazy-mac.com/embedding-search/mcp"
    }
  }
}

遠端端點

https://api.lazy-mac.com/embedding-search/mcpstreamable-http

它能做什麼

工具清單

工具（3）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪generate_embeddings(text, model)

Generate vector embeddings for one or more texts using Cloudflare Workers AI (bge-base-en-v1.5, 768-dim).

輸入結構描述

{
  "type": "object",
  "properties": {
    "text": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Text or array of texts to embed"
    },
    "model": {
      "type": "string",
      "description": "CF AI model ID override"
    }
  },
  "required": [
    "text"
  ]
}
🟢semantic_search(query, documents, top_k, model)

Rank a list of documents against a query using cosine similarity of bge embeddings. Returns top-k matches with scores.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query"
    },
    "documents": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Candidate documents to rank"
    },
    "top_k": {
      "type": "integer",
      "description": "Number of results (default 5)"
    },
    "model": {
      "type": "string",
      "description": "CF AI model ID override"
    }
  },
  "required": [
    "query",
    "documents"
  ]
}
🟢compute_similarity(text_a, text_b, model)

Compute cosine similarity between two texts. Returns score in [-1,1]. Useful for dedup and relatedness.

輸入結構描述

{
  "type": "object",
  "properties": {
    "text_a": {
      "type": "string"
    },
    "text_b": {
      "type": "string"
    },
    "model": {
      "type": "string"
    }
  },
  "required": [
    "text_a",
    "text_b"
  ]
}

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