Extract PDF metadata

tw_extract_pdf_metadata

GenericMIT

提取 PDF 元資料（不含內文）— 檔案 inventory / 分類前置判斷。

Args:
    source: PDF URL 或 base64-encoded 內容。

Returns: page_count + title/author/subject/creator/producer/dates/encrypted。

Input schema

{
  "properties": {
    "source": {
      "title": "Source",
      "type": "string"
    }
  },
  "required": [
    "source"
  ],
  "title": "extract_pdf_metadataArguments",
  "type": "object"
}

How to call

Once your Twinkle Hub MCP client is configured, your agent will see tw_extract_pdf_metadata. Just ask it to call — example:

# Ask Claude / any MCP client:
請用 tw_extract_pdf_metadata 處理 "…"。

# It will call:
tw_extract_pdf_metadata(input="…")

Haven't set up a client yet?

Claude Desktop in 3 minutes — download the .mcpb and double-click, or see docs for other clients.

See user docs