file2markdown

Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.

我該用這個嗎

品質與安全性

B
說明品質
95%
結構描述完整度
53%
命名品質
95%
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

~575Token(工具定義)
~546 B典型回應大小
極小的注意力影響(128k 上下文的 0.45%)

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": {
    "file2markdown": {
      "url": "https://mcp.file2markdown.ai/mcp"
    }
  }
}

遠端端點

https://mcp.file2markdown.ai/mcpstreamable-http

它能做什麼

工具清單

工具(4)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢convert_url(url, filename_hint, quality_check)

Fetch a URL (web page, PDF, Office doc, and more) and convert it to Markdown. Works on publicly accessible URLs. Web pages are converted from their served HTML; JavaScript-rendered content may be incomplete. Optional filename_hint (e.g. "report.pdf") helps format detection when the URL has no file extension. The result carries a `quality` object (output-health check of the returned Markdown: status review / no_issues_detected / not_evaluated, coverage and a list of issues with line locations). quality_check="basic" (default) runs only local deterministic checks. quality_check="ai" additionally sends selected excerpts of the CONVERTED text to TypeSafe for narrow yes/no judgments (garbled text, hard-wrapped prose, broken tables); it is off unless requested. No check compares against the source document.

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "title": "Url",
      "type": "string"
    },
    "filename_hint": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Filename Hint"
    },
    "quality_check": {
      "default": "basic",
      "title": "Quality Check",
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "title": "convert_urlArguments"
}
⚪convert_base64(content_base64, filename, quality_check)

Convert base64-encoded file contents to Markdown. filename is required and drives format detection (e.g. "report.docx"). Intended for programmatic MCP clients; for anything with a URL, prefer convert_url. quality_check: "basic" (default) attaches local output-health checks in the `quality` field; "ai" additionally sends selected excerpts of the converted text to TypeSafe for narrow yes/no judgments. See convert_url.

輸入結構描述

{
  "type": "object",
  "properties": {
    "content_base64": {
      "title": "Content Base64",
      "type": "string"
    },
    "filename": {
      "title": "Filename",
      "type": "string"
    },
    "quality_check": {
      "default": "basic",
      "title": "Quality Check",
      "type": "string"
    }
  },
  "required": [
    "content_base64",
    "filename"
  ],
  "title": "convert_base64Arguments"
}
🟢list_supported_formats

List supported input formats, per-tier limits, and which features need Pro. Single source of truth — do not claim capabilities beyond what this returns.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "title": "list_supported_formatsArguments"
}
🟢usage_status

Check your tier and remaining conversions before burning a call.

輸入結構描述

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

建議的提示詞

list_items
List all [items] available in file2markdown
預期的工具: list_supported_formats
browse_collection
Show me the [collection] from file2markdown
預期的工具: list_supported_formats

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本4 個工具
已驗證未記錄版本4 個工具