Combien d'outils expose com.ainetcafe/netcafe-docs ?

com.ainetcafe/netcafe-docs expose 23 outil(s). Le coût de contexte pour les charger tous est d'environ 4208 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Fichiers & Documents / com.ainetcafe/netcafe-docs

com.ainetcafe/netcafe-docs

serveur MCP (Model Context Protocol) · netcafe-docs 1.5.0

▸ Fichiers & Documents

[ Non encore testé ]

Verdict MCP Hub
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.

?Type / transport

?Accès

~4208 tokensCoût de contexte

23Outils

Est-ce que com.ainetcafe/netcafe-docs est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.ainetcafe/netcafe-docs » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 23 outils

check_job≈ 270 tokens
Get the status or result of a job started by deep_research, translate_pdf, or make_slides. Poll every 15-30 seconds until status is "done" or "error". While work is pending, follow retry_after_seconds and next_action; when complete, prefer structured_result when present. Example — GET https://ainetcafe.com/t/check_job?job_id=<id-from-a-job-tool>
Paramètres, retour & exemple (1)
Paramètres
- job_id · string · requis
  The job_id returned when the task was started.
Exemple d'appel
```
{"name": "check_job", "arguments": {"job_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"kind": "texte", "error": "texte", "job_id": "texte", "result": "texte", "status": "texte", "is_terminal": true, "next_action": {}, "structured_result": "texte", "retry_after_seconds": 1}}
```
check_resume≈ 178 tokens
Check a resume (PDF or .docx) the way an applicant tracking system reads it: is the text extractable, are email/phone/sections findable, do multi-column layouts, tables or emoji break parsing. Returns a score plus concrete fixes ordered by impact — like the W3C validator, but for resumes.
Paramètres, retour & exemple (1)
Paramètres
- url · string · requis
  Public URL of the resume (PDF or .docx).
Exemple d'appel
```
{"name": "check_resume", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
convert_to_pdf≈ 177 tokens
Print-quality PDF from a URL or raw HTML via self-hosted Gotenberg (headless Chromium). Returns a hosted PDF download URL. Example — GET https://ainetcafe.com/t/convert_to_pdf?url=https://example.com
Paramètres, retour & exemple (2)
Paramètres
- url · string · optionnel
  Page URL to convert (either url or html is required).
- html · string · optionnel
  Raw HTML to convert (alternative to url).
Exemple d'appel
```
{"name": "convert_to_pdf", "arguments": {"url": "texte", "html": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
csv_to_qbo≈ 265 tokens
Convert a transaction CSV into a .qbo / OFX bank-feed file that QuickBooks and similar accounting software import directly. Needs date, description and amount columns (or debit + credit). Pairs with extract_statement: statement PDF in, importable bank feed out.
Paramètres, retour & exemple (5)
Paramètres
- csv · string · optionnel
  CSV content with a header row.
- url · string · optionnel
  Or a link to the CSV.
- bank_id · string · optionnel
  Routing / bank identifier, if your import asks for one.
- currency · string · optionnel
  Three-letter currency code, default USD.
- account_id · string · optionnel
  Your account number as the accounting software expects it.
Exemple d'appel
```
{"name": "csv_to_qbo", "arguments": {"csv": "texte", "url": "texte", "bank_id": "texte", "currency": "texte", "account_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
deep_research≈ 318 tokens
Start an autonomous web research task. The agent plans sub-questions, searches the web, reads the sources and writes a report with citations — this is real research, not a single model call, and takes 2-5 minutes. Returns a job_id immediately; poll check_job to get the report. Use this when you need sourced, current information rather than what a model already knows. Powered by gpt-researcher (29k stars) hosted at AI NetCafé. Example — tools/call deep_research {"topic":"State of MCP adoption in 2026?"} → poll check_job
Paramètres, retour & exemple (2)
Paramètres
- depth · string · optionnel · quick | standard
  quick = outline only (~1 min); standard = full cited report (~3 min). Default standard.
- topic · string · requis
  The research question. Phrase it as a question, not a keyword.
Exemple d'appel
```
{"name": "deep_research", "arguments": {"topic": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte", "status": "texte", "poll_interval_seconds": 1}}
```
doc_translate_cn≈ 82 tokens
文档翻译成中文,保留段落结构。逐段翻译并核对段落条数进出一致 —— 漏译最常见的形态就是整段消失,这里会当场发现。入参 url(文档链接)或 text,可选 target(默认 zh)。自证不通过不计费。
Paramètres, retour & exemple (3)
Paramètres
- url · ? · optionnel
- text · string · optionnel
- target · string · optionnel
Exemple d'appel
```
{"name": "doc_translate_cn", "arguments": {"url": "texte", "text": "texte", "target": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
extract_invoices≈ 249 tokens
Give it up to 20 invoice URLs (PDF or page images) and get back one table ready to post: number, date, seller, buyer, net / tax / gross, currency. Every row is checked in code — net + tax must equal gross — and the batch total is re-added independently, so a row the model misread is flagged with the exact difference instead of quietly landing in your books. Mixed currencies get no batch total on purpose: adding them together would be an accounting error. CSV is UTF-8 with BOM so Excel opens it right.
Paramètres, retour & exemple (1)
Paramètres
- urls · string · requis
  Invoice URLs — comma-separated, or pass an array. Up to 20 per call.
Exemple d'appel
```
{"name": "extract_invoices", "arguments": {"urls": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
extract_statement≈ 210 tokens
Turn a bank statement or transaction PDF into a clean transaction table (JSON + CSV), then cross-check it: opening + credits - debits must equal the stated closing balance. If it does not balance you get the exact difference and which row the running balance first breaks at — so you know whether the table is safe to use for accounting. Text-layer PDFs only (scanned images not yet supported).
Paramètres, retour & exemple (1)
Paramètres
- url · string · requis
  Public URL of the statement PDF.
Exemple d'appel
```
{"name": "extract_statement", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
extract_tables≈ 221 tokens
Extract tables from a PDF into structured rows (JSON + CSV). Pass fields to force a fixed set of columns — that aligns a pile of documents that each name their headers differently into one consistent table. Rows the model was unsure about are flagged rather than guessed. Text-layer PDFs only.
Paramètres, retour & exemple (2)
Paramètres
- url · string · requis
  Public URL of the PDF.
- fields · string · optionnel
  Optional comma-separated target columns, e.g. "invoice_no,supplier,date,amount". Omit to infer from the header.
Exemple d'appel
```
{"name": "extract_tables", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
fix_csv_encoding≈ 171 tokens
Detect the real encoding of a CSV (GB18030, Shift-JIS, Windows-1252…), repair mojibake (UTF-8 that was read as Latin-1, e.g. "Ã©"), and re-emit UTF-8 with a BOM so Excel opens it correctly.
Paramètres, retour & exemple (2)
Paramètres
- url · string · optionnel
  Public URL of the CSV.
- text · string · optionnel
  Or paste the CSV content directly.
Exemple d'appel
```
{"name": "fix_csv_encoding", "arguments": {"url": "texte", "text": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
make_slides≈ 292 tokens
Turn a topic or an outline into a real downloadable .pptx file — not a link into someone's web editor. Returns a job_id; poll check_job for the download URL. Usually 1-3 minutes. Powered by Presenton (open source) hosted at AI NetCafé. Example — tools/call make_slides {"topic":"Q3 review","slides":8} → poll check_job
Paramètres, retour & exemple (4)
Paramètres
- topic · string · requis
  The topic, or a full outline to follow.
- slides · integer · optionnel
  Number of slides (default 8).
- language · string · optionnel
  Output language, e.g. "Chinese", "English". Default Chinese.
- instructions · string · optionnel
  Optional extra guidance on style or emphasis.
Exemple d'appel
```
{"name": "make_slides", "arguments": {"topic": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte", "status": "texte", "poll_interval_seconds": 1}}
```
meeting_pack≈ 72 tokens
会议录音 → 纪要包 PDF:转写、要点、决议、待办。纪要里点名的负责人会与转写原文比对 —— 把任务安排给一个从没在录音里出现过的人,报告会判不通过。入参 url(音频直链)。自证不通过不计费。
Paramètres, retour & exemple (2)
Paramètres
- url · string · optionnel
- audio · ? · optionnel
Exemple d'appel
```
{"name": "meeting_pack", "arguments": {"url": "texte", "audio": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
pdf_add_page_numbers≈ 323 tokens
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}".
Paramètres, retour & exemple (7)
Paramètres
- url · string · requis
  Public URL of the PDF.
- text · string · optionnel
  Template, default "{n}". Use {n} and {total}.
- style · string · optionnel
  arabic (default) | roman (i, ii, iii) | ROMAN (I, II, III)
- position · string · optionnel
  bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right
- start_at · integer · optionnel
  Number to start from (default 1).
- font_size · integer · optionnel
  Font size, default 10.
- skip_first · integer · optionnel
  Leave this many leading pages unnumbered, e.g. 1 for a cover.
Exemple d'appel
```
{"name": "pdf_add_page_numbers", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
pdf_page_count≈ 55 tokens
Count pages and report each page size of a PDF (by URL).
Paramètres, retour & exemple (1)
Paramètres
- url · ? · optionnel
Exemple d'appel
```
{"name": "pdf_page_count", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
pdf_to_markdown≈ 178 tokens
Convert a PDF (or a scanned page image) into clean Markdown that keeps headings, lists and tables, and puts multi-column pages in the right reading order. Text-layer PDFs are read exactly and cost far less; images go through a vision model.
Paramètres, retour & exemple (1)
Paramètres
- url · string · requis
  Public URL of the PDF, or of a page image (png/jpg) for scanned documents.
Exemple d'appel
```
{"name": "pdf_to_markdown", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
pdf_watermark≈ 68 tokens
Stamp diagonal text watermark on every page of a PDF (by URL). text = the watermark.
Paramètres, retour & exemple (2)
Paramètres
- url · ? · optionnel
- text · string · optionnel
Exemple d'appel
```
{"name": "pdf_watermark", "arguments": {"url": "texte", "text": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
pptx_to_pdf≈ 50 tokens
PowerPoint .pptx (by URL) → PDF handout.
Paramètres, retour & exemple (1)
Paramètres
- url · ? · optionnel
Exemple d'appel
```
{"name": "pptx_to_pdf", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
redact_text≈ 210 tokens
Strip emails, phone numbers, ID numbers, API keys, private keys, JWTs, card numbers and IPs out of text, returning the redacted text plus a mapping table to restore them afterwards. Rule-based only — no model sees the input. The same value always maps to the same placeholder, so the answer can be restored.
Paramètres, retour & exemple (2)
Paramètres
- only · string · optionnel
  Optional comma-separated subset, e.g. "EMAIL,API_KEY,PRIVATE_KEY".
- text · string · requis
  The text to redact.
Exemple d'appel
```
{"name": "redact_text", "arguments": {"text": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
transcribe_audio≈ 203 tokens
Fetch an audio file from a URL and transcribe it to text with open-source Whisper (100 languages, self-hosted). Good for voice memos, podcast clips and meeting recordings up to ~15 MB. Example — GET https://ainetcafe.com/t/transcribe_audio?url=<public-audio-url>
Paramètres, retour & exemple (2)
Paramètres
- url · string · requis
  Public URL of the audio file (mp3/wav/m4a/ogg, ≤15 MB).
- language · string · optionnel
  Hint language code like "zh", "en"; default auto-detect.
Exemple d'appel
```
{"name": "transcribe_audio", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
translate_pdf≈ 346 tokens
Translate a PDF from a URL while preserving the original layout — formulas, figures and two-column academic typesetting stay intact, unlike ordinary translators that flatten the document. Returns a job_id; poll check_job for the download links (translated-only and bilingual side-by-side). Typically 20-60 seconds for a few pages. Powered by PDFMathTranslate (36k stars) hosted at AI NetCafé. Example — tools/call translate_pdf {"url":"<pdf-url>","target":"zh"} → poll check_job
Paramètres, retour & exemple (3)
Paramètres
- url · string · requis
  Direct URL to the PDF (e.g. an arXiv PDF link).
- pages · string · optionnel · first | first5 | all
  How much to translate. first = 1 page, first5 = first 5 pages (default), all = whole document (slow and expensive).
- lang_to · string · optionnel
  Target language, e.g. "Simplified Chinese", "Japanese". Default Simplified Chinese.
Exemple d'appel
```
{"name": "translate_pdf", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte", "status": "texte", "poll_interval_seconds": 1}}
```
webpage_to_docx≈ 57 tokens
Any article URL → Word .docx (rendered page → clean document).
Paramètres, retour & exemple (1)
Paramètres
- url · ? · optionnel
Exemple d'appel
```
{"name": "webpage_to_docx", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
what_can_you_do≈ 248 tokens
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.
Paramètres, retour & exemple (1)
Paramètres
- task · string · requis
  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"
Exemple d'appel
```
{"name": "what_can_you_do", "arguments": {"task": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
xlsx_to_pdf≈ 46 tokens
Excel .xlsx (by URL) → PDF.
Paramètres, retour & exemple (1)
Paramètres
- url · ? · optionnel
Exemple d'appel
```
{"name": "xlsx_to_pdf", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://ainetcafe.com/mcp/docs?s=registry