netcafe-docflow
Markdown in, any format out. PDFs merged, split, watermarked. Runs on our own doc engines.
使うべきか
品質と安全性
検出事項（7）
- LOWTool 'md_to_html' description lacks action verbmd_to_html 内
- LOWTool 'md_to_epub' description lacks action verbmd_to_epub 内
- LOWTool 'docx_to_md' description lacks action verbdocx_to_md 内
- LOWTool 'merge_pdf' description lacks action verbmerge_pdf 内
- LOWTool 'split_pdf' description lacks action verbsplit_pdf 内
- LOWTool 'pdf_watermark' description lacks action verbpdf_watermark 内
- LOWTool 'pdf_rotate' description lacks action verbpdf_rotate 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"netcafe-docflow": {
"url": "https://ainetcafe.com/mcp/paper?s=registry"
}
}
}リモートエンドポイント
https://ainetcafe.com/mcp/paper?s=registrystreamable-httpできること
ツール一覧
ツール（13）
🟢what_can_you_do(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.
入力スキーマ
{
"type": "object",
"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\""
}
},
"required": [
"task"
]
}出力スキーマ
{
"type": "object",
"additionalProperties": true
}🟢pdf_add_page_numbers(url, style, start_at, skip_first, position, ...)
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}".
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public URL of the PDF."
},
"style": {
"type": "string",
"description": "arabic (default) | roman (i, ii, iii) | ROMAN (I, II, III)"
},
"start_at": {
"type": "integer",
"description": "Number to start from (default 1)."
},
"skip_first": {
"type": "integer",
"description": "Leave this many leading pages unnumbered, e.g. 1 for a cover."
},
"position": {
"type": "string",
"description": "bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right"
},
"text": {
"type": "string",
"description": "Template, default \"{n}\". Use {n} and {total}."
},
"font_size": {
"type": "integer",
"description": "Font size, default 10."
}
},
"required": [
"url"
]
}出力スキーマ
{
"type": "object",
"additionalProperties": true
}🟡md_to_pdf(markdown, url)
Markdown → styled PDF. Send markdown text or a URL to a .md file, get a print-ready PDF back.
入力スキーマ
{
"type": "object",
"properties": {
"markdown": {},
"url": {}
},
"additionalProperties": true
}⚪md_to_docx(markdown, url)
Markdown → Word (.docx). The deliverable your non-technical colleagues actually open.
入力スキーマ
{
"type": "object",
"properties": {
"markdown": {},
"url": {}
},
"additionalProperties": true
}⚪md_to_pptx(markdown, url)
Markdown (heading per slide) → PowerPoint .pptx. Fastest structured route to a deck.
入力スキーマ
{
"type": "object",
"properties": {
"markdown": {},
"url": {}
},
"additionalProperties": true
}⚪md_to_html(markdown, url)
Markdown → standalone styled HTML page (single file, inline CSS).
入力スキーマ
{
"type": "object",
"properties": {
"markdown": {},
"url": {}
},
"additionalProperties": true
}⚪md_to_epub(markdown, url, title, author)
Markdown → EPUB e-book, with title and author metadata.
入力スキーマ
{
"type": "object",
"properties": {
"markdown": {},
"url": {},
"title": {
"type": "string"
},
"author": {
"type": "string"
}
},
"additionalProperties": true
}⚪docx_to_md(url)
Word .docx (by URL) → clean Markdown. Feed documents to your agent pipeline.
入力スキーマ
{
"type": "object",
"properties": {
"url": {}
},
"additionalProperties": true
}⚪merge_pdf(urls)
Merge several PDFs (by URL) into one. urls = comma-separated links, in order.
入力スキーマ
{
"type": "object",
"properties": {
"urls": {
"type": "string"
}
},
"additionalProperties": true
}🟢split_pdf(url, from, to)
Extract a page range from a PDF (by URL) into a new PDF. from/to are 1-based page numbers.
入力スキーマ
{
"type": "object",
"properties": {
"url": {},
"from": {
"type": "number"
},
"to": {
"type": "number"
}
},
"additionalProperties": true
}🟢pdf_page_count(url)
Count pages and report each page size of a PDF (by URL).
入力スキーマ
{
"type": "object",
"properties": {
"url": {}
},
"additionalProperties": true
}⚪pdf_watermark(text, url)
Stamp diagonal text watermark on every page of a PDF (by URL). text = the watermark.
入力スキーマ
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"url": {}
},
"additionalProperties": true
}⚪pdf_rotate(url, degrees)
Rotate all pages of a PDF (by URL) by 90/180/270 degrees.
入力スキーマ
{
"type": "object",
"properties": {
"url": {},
"degrees": {
"type": "number"
}
},
"additionalProperties": true
}コミュニティ
エビデンス