# NetCafe Docs Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## NetCafe Docs

Extract and verify invoices, statements and tables from PDFs with built-in arithmetic checks.

- Record: https://musedirectory.ai/connector/netcafe-docs
- Category: Finance & Bills
- Developer: AI NetCafé (https://ainetcafe.com/mcp.html)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 716ms, checked 2026-09-28T08:01:49Z
- Endpoint: https://ainetcafe.com/mcp/docs?s=registry
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-09-24T10:41:09Z)
- Source: Found in the official MCP Registry (com.ainetcafe/netcafe-docs) https://registry.modelcontextprotocol.io/v0/servers?search=com.ainetcafe%2Fnetcafe-docs

Converts bank statements and invoices into verified transaction tables and QBO files for accounting software. Extracts tables from PDFs, reconciles balances, and flags discrepancies. Also handles document format conversion, transcription, and research tasks.

Example request: "Extract my monthly bank statement PDF and convert it to a QuickBooks-compatible file, checking that the totals balance."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use NetCafe Docs to help me. It is a free service with an MCP server at https://ainetcafe.com/mcp/docs?s=registry. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- what_can_you_do: 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 le
- redact_text: 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 
- csv_to_qbo: 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.
- check_resume: 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
- pdf_to_markdown: 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.
- extract_tables: 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-lay
- extract_statement: 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 
- extract_invoices: 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
- pdf_add_page_numbers: 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}".
- fix_csv_encoding: Detect the real encoding of a CSV (GB18030, Shift-JIS, Windows-1252…), repair mojibake (UTF-8 that was read as Latin-1, e.g. "é"), and re-emit UTF-8 with a BOM so Excel opens it correctly.
- transcribe_audio: 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>
- convert_to_pdf: 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
- deep_research: 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. Us
- check_job: 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 
- translate_pdf: 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-
- make_slides: 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":"Q
- pdf_page_count: Count pages and report each page size of a PDF (by URL).
- pdf_watermark: Stamp diagonal text watermark on every page of a PDF (by URL). text = the watermark.
- xlsx_to_pdf: Excel .xlsx (by URL) → PDF.
- pptx_to_pdf: PowerPoint .pptx (by URL) → PDF handout.
- webpage_to_docx: Any article URL → Word .docx (rendered page → clean document).
- meeting_pack: 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。
- doc_translate_cn: 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。

Screening checks:
- MCP handshake: pass (Answered in 412ms)
- Domain against threat feeds (Cloudflare security DNS): pass (ainetcafe.com not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (23 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 57 days ago)
- AI review of purpose and tool behavior: pass (No concerns)