mcp

See how ChatGPT, Claude, Perplexity, and Gemini cite brands, prompts, and sources.

我該用這個嗎

品質與安全性

A
說明品質
90%
結構描述完整度
72%
命名品質
100%
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

~446Token(工具定義)
~310 B典型回應大小
極小的注意力影響(128k 上下文的 0.35%)

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": {
    "mcp": {
      "command": "npx",
      "args": [
        "@parse-gl/mcp"
      ]
    }
  }
}

可執行的套件

npm@parse-gl/mcp1.0.0stdio

遠端端點

https://mcp.parse.gl/mcpstreamable-http

它能做什麼

工具清單

工具(6)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢parse_search(query, types, limit)

Find brands, organic AI prompts, and market niches for marketer research. Use this first when the user names a brand, category, or AI visibility question.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "types": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "brands",
          "prompts",
          "niches"
        ]
      }
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 10
    }
  },
  "required": [
    "query"
  ]
}
🟢parse_get_brand(slug_or_id)

Fetch a concise public marketing brief for one brand, including Parse score, strengths, weak spots, top prompts, citation sources, related brands, and next research questions.

輸入結構描述

{
  "type": "object",
  "properties": {
    "slug_or_id": {
      "type": "string"
    }
  },
  "required": [
    "slug_or_id"
  ]
}
🟢parse_get_prompt(slug)

Fetch one public organic prompt by slug when the user wants to inspect the exact AI-search question behind a result.

輸入結構描述

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string"
    }
  },
  "required": [
    "slug"
  ]
}
🟢parse_get_stats

Explain the public Parse index scale and freshness: tracked brands, organic prompts, and citation observations.

輸入結構描述

{
  "type": "object",
  "properties": {}
}
🟢search(query, limit)

Compatibility alias for parse_search. Use for clients that expect a generic search tool.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 10
    }
  },
  "required": [
    "query"
  ]
}
🟢fetch(id)

Compatibility alias that resolves fetch IDs like brand:stripe or prompt:best-crm into JSON-text results with human-readable text.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ]
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本6 個工具
已驗證未記錄版本6 個工具