MCP Server

netcafe-docflow

com.ainetcafe/netcafe-docflow
Media & Content Productivity Public & reachable MCP 2026-07-28

What this MCP does

Converts Markdown and DOCX documents and performs PDF merging, splitting, rotation, page numbering, watermarking, and inspection.

docx_to_md
docx to md
Word .docx (by URL) → clean Markdown. Feed documents to your agent pipeline.
Input schema
{'type': 'object', 'properties': {'url': {}}, 'additionalProperties': True}
md_to_docx
md to docx
Markdown → Word (.docx). The deliverable your non-technical colleagues actually open.
Input schema
{'type': 'object', 'properties': {'url': {}, 'markdown': {}}, 'additionalProperties': True}
md_to_epub
md to epub
Markdown → EPUB e-book, with title and author metadata.
Input schema
{'type': 'object', 'properties': {'url': {}, 'title': {'type': 'string'}, 'author': {'type': 'string'}, 'markdown': {}}, 'additionalProperties': True}
md_to_html
md to html
Markdown → standalone styled HTML page (single file, inline CSS).
Input schema
{'type': 'object', 'properties': {'url': {}, 'markdown': {}}, 'additionalProperties': True}
md_to_pdf
md to pdf
Markdown → styled PDF. Send markdown text or a URL to a .md file, get a print-ready PDF back.
Input schema
{'type': 'object', 'properties': {'url': {}, 'markdown': {}}, 'additionalProperties': True}
md_to_pptx
md to pptx
Markdown (heading per slide) → PowerPoint .pptx. Fastest structured route to a deck.
Input schema
{'type': 'object', 'properties': {'url': {}, 'markdown': {}}, 'additionalProperties': True}
merge_pdf
merge pdf
Merge several PDFs (by URL) into one. urls = comma-separated links, in order.
Input schema
{'type': 'object', 'properties': {'urls': {'type': 'string'}}, 'additionalProperties': True}
pdf_add_page_numbers
Add page numbers to a PDF
Stamp page numbers or footer text onto every page of a PDF. Supports a starting number, roman numerals, skipping a cover page, position and font size — the combination Acrobat cannot do without scripting. Template supports {n} and {total}, e.g. "Page {n} of {total}".
Read only Idempotent
Input schema
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Public URL of the PDF.'}, 'text': {'type': 'string', 'description': 'Template, default "{n}". Use {n} and {total}.'}, 'style': {'type': 'string', 'description': 'arabic (default) | roman (i, ii, iii) | ROMAN (I, II, III)'}, 'position': {'type': 'string', 'description': 'bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right'}, 'start_at': {'type': 'integer', 'description': 'Number to start from (default 1).'}, 'font_size': {'type': 'integer', 'description': 'Font size, default 10.'}, 'skip_first': {'type': 'integer', 'description': 'Leave this many leading pages unnumbered, e.g. 1 for a cover.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
pdf_page_count
pdf page count
Count pages and report each page size of a PDF (by URL).
Input schema
{'type': 'object', 'properties': {'url': {}}, 'additionalProperties': True}
pdf_rotate
pdf rotate
Rotate all pages of a PDF (by URL) by 90/180/270 degrees.
Input schema
{'type': 'object', 'properties': {'url': {}, 'degrees': {'type': 'number'}}, 'additionalProperties': True}
pdf_watermark
pdf watermark
Stamp diagonal text watermark on every page of a PDF (by URL). text = the watermark.
Input schema
{'type': 'object', 'properties': {'url': {}, 'text': {'type': 'string'}}, 'additionalProperties': True}
split_pdf
split pdf
Extract a page range from a PDF (by URL) into a new PDF. from/to are 1-based page numbers.
Input schema
{'type': 'object', 'properties': {'to': {'type': 'number'}, 'url': {}, 'from': {'type': 'number'}}, 'additionalProperties': True}
what_can_you_do
Find the right tool for a task
Describe a task in plain language (any language) and get back exactly which tools on this server do it, with ready-to-run example calls — instead of reading the whole catalogue and guessing. Also returns multi-step recipes when a task needs several tools chained (invoices to a ledger, a bank statement reconciled, a messy CSV turned into a deliverable). Deterministic and free: it calls no model, costs nothing, and never runs out of quota. Call this FIRST when you are not sure what this server offers.
Read only Idempotent
Input schema
{'type': 'object', 'required': ['task'], 'properties': {'task': {'type': 'string', 'description': 'What you are trying to do, e.g. "reconcile a bank statement against my books" or "把一堆发票整理成能入账的表格"'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
Added
pdf_rotate
Sept. 17, 2026, 12:33 p.m.
Added
pdf_watermark
Sept. 17, 2026, 12:33 p.m.
Added
pdf_page_count
Sept. 17, 2026, 12:33 p.m.
Added
split_pdf
Sept. 17, 2026, 12:33 p.m.
Added
merge_pdf
Sept. 17, 2026, 12:33 p.m.
Added
docx_to_md
Sept. 17, 2026, 12:33 p.m.
Added
md_to_epub
Sept. 17, 2026, 12:33 p.m.
Added
md_to_html
Sept. 17, 2026, 12:33 p.m.
Added
md_to_pptx
Sept. 17, 2026, 12:33 p.m.
Added
md_to_docx
Sept. 17, 2026, 12:33 p.m.
Added
md_to_pdf
Sept. 17, 2026, 12:33 p.m.
Added
pdf_add_page_numbers
Sept. 17, 2026, 12:33 p.m.
Added
what_can_you_do
Sept. 17, 2026, 12:33 p.m.