MCP MeasureMCP Measure

索引已觀測

RawMark

Documents to Markdown: PDF, DOCX, PPTX, XLSX, HTML. Scanned PDF pages read by AI.

我該用這個嗎

品質與安全性

B
說明品質
100%
結構描述完整度
43%
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

~363Token（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 0.28%）

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": {
    "rawmark": {
      "url": "https://rawmark.tech/mcp"
    }
  }
}

遠端端點

https://rawmark.tech/mcpstreamable-http

它能做什麼

工具清單

工具（2）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢convert_document(url, content_base64, filename, ai_accuracy)

Convert a PDF, DOCX, PPTX, XLSX, HTML or TXT file to Markdown. Give either `url` (a public link to the file) or `content_base64` plus `filename`. Scanned PDF pages are read by an AI vision model. `ai_accuracy` (paid plans) reads every PDF page with AI for exact tables. Each call uses one conversion.

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Url"
    },
    "content_base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Content Base64"
    },
    "filename": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Filename"
    },
    "ai_accuracy": {
      "default": false,
      "title": "Ai Accuracy",
      "type": "boolean"
    }
  },
  "title": "convert_documentArguments"
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "convert_documentOutput"
}
🟢get_usage

What the caller's RawMark plan has left: conversions for a license key, or today's free conversions.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "title": "get_usageArguments"
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "get_usageOutput"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本2 個工具