Extract PDF pages

tw_extract_pdf_pages

GenericMIT

提取指定頁碼之 PDF 內文（節省成本，跳過 boilerplate）。

Args:
    source: PDF URL 或 base64-encoded。
    pages: 頁碼字串（1-indexed），支援 "1,3,5"、"2-5"、"1,3-5,8"。

Input schema

{
  "properties": {
    "source": {
      "title": "Source",
      "type": "string"
    },
    "pages": {
      "title": "Pages",
      "type": "string"
    }
  },
  "required": [
    "source",
    "pages"
  ],
  "title": "extract_pdf_pagesArguments",
  "type": "object"
}

How to call

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

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

# It will call:
tw_extract_pdf_pages(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