MCP 服务器

EasyPDF

io.github.Lorenzino69/easypdf
生产力 公开且可连接 MCP 2025-11-25

此 MCP 可以做什么

Manipulates PDF files by compressing, merging, splitting, rotating, extracting, numbering, protecting, and unlocking pages.

add_page_numbers
Add page numbers
Add page numbers to a PDF.
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The PDF to number.'}, 'position': {'type': 'string', 'default': 'bottom-center', 'description': '"bottom-center" (default), "bottom-left", "bottom-right", "top-center", "top-left" or "top-right".'}, 'start_number': {'type': 'integer', 'default': 1, 'description': 'Number printed on the first page. Default 1.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
compress_pdf
Compress PDF
Compress a PDF to reduce its file size while keeping it readable.
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The PDF to compress (shared in the conversation).'}, 'quality': {'type': 'string', 'default': 'medium', 'description': '"low" (smallest file), "medium" (balanced, default) or "high" (best visual quality).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
edit_pdf_text
Edit text in PDF
Change, correct or delete text INSIDE the original PDF, keeping its fonts, sizes, colors and layout. Use this whenever the user wants their existing PDF updated rather than a new document: fix a typo, change a date, amount, name or address, update a CV or a price list, translate a heading, remove a line. Read the PDF first, then pass one edit per change with `find` copied exactly as printed in the document. Dates and amounts written differently in the PDF (12/08/2026 vs August 12, 2026; 1240 vs 1,240.00) are matched and rewritten in the document's format.
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file', 'edits'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The PDF to edit (shared in the conversation).'}, 'edits': {'type': 'array', 'items': {'type': 'object', 'required': ['find', 'replace'], 'properties': {'find': {'type': 'string', 'description': 'Text to replace, copied exactly as it is printed in the PDF (same spelling, accents and punctuation). Keep it short: one line or a few words is most reliable.'}, 'page': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': '1-based page number to limit this change to. Omit to change every occurrence in the document.'}, 'replace': {'type': 'string', 'description': 'New text written in place of `find`. An empty string deletes the text.'}}, 'description': 'One change to write into the PDF.'}, 'description': 'Changes to write, applied in order. Each one replaces every\noccurrence of `find` (only on `page` when given).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
extract_pages
Extract pages
Extract specific pages from a PDF into a new PDF (pages are 1-indexed).
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file', 'page_numbers'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The source PDF.'}, 'page_numbers': {'type': 'array', 'items': {'type': 'integer'}, 'description': 'Pages to keep, e.g. [1, 3, 5]. Order is preserved.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
merge_pdfs
Merge PDFs
Merge several PDF files into a single document, in the given order.
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['files'], 'properties': {'files': {'type': 'array', 'items': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'A file shared in the ChatGPT conversation (user upload).'}, 'description': 'Two or more PDFs shared in the conversation, in the order to merge them.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
protect_pdf
Protect PDF with password
Protect a PDF with a password (AES-256 encryption).
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file', 'password'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The PDF to protect.'}, 'password': {'type': 'string', 'description': 'Password that will be required to open the PDF.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
rotate_pdf
Rotate PDF
Rotate all pages, or selected pages, of a PDF.
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file', 'angle'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The PDF to rotate.'}, 'angle': {'type': 'integer', 'description': '90, 180 or 270 degrees (clockwise).'}, 'pages': {'anyOf': [{'type': 'array', 'items': {'type': 'integer'}}, {'type': 'null'}], 'default': None, 'description': 'Optional 1-indexed page numbers to rotate; omit to rotate every page.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
split_pdf
Split PDF
Split a PDF into several smaller PDFs.
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The PDF to split.'}, 'pages_per_file': {'type': 'integer', 'default': 1, 'description': 'Number of pages in each output file (default 1: one file per page).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
unlock_pdf
Remove PDF password
Remove the password protection from a PDF you own.
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['file', 'password'], 'properties': {'file': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string', 'description': 'ChatGPT file identifier.'}, 'file_name': {'type': 'string', 'default': '', 'description': 'Original file name, e.g. report.pdf.'}, 'mime_type': {'type': 'string', 'default': '', 'description': 'MIME type of the file, e.g. application/pdf.'}, 'download_url': {'type': 'string', 'description': 'URL from which the file can be downloaded.'}}, 'description': 'The password-protected PDF.'}, 'password': {'type': 'string', 'description': 'Its current password.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
已添加
edit_pdf_text
2026年10月1日 02:45
已添加
add_page_numbers
2026年9月17日 12:43
已添加
unlock_pdf
2026年9月17日 12:43
已添加
protect_pdf
2026年9月17日 12:43
已添加
rotate_pdf
2026年9月17日 12:43
已添加
extract_pages
2026年9月17日 12:43
已添加
split_pdf
2026年9月17日 12:43
已添加
merge_pdfs
2026年9月17日 12:43
已添加
compress_pdf
2026年9月17日 12:43