Connect Netcafe Docs and your agent gets 23 tools, among them check_job, check_resume, convert_to_pdf. It answers at https://ainetcafe.com/mcp/docs?s=registry over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 11 times since 4 September 2026; the last check, on 7 November 2026, succeeded.
Statements, tables and PDFs turned into checked data — with a reconciliation self-check.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 Inputs: job_id |
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 Inputs: 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 Inputs: url, html |
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, impo Inputs: csv, url, account_id, bank_id, currency |
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 immediate Inputs: topic, depth |
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。 Inputs: text, url, target |
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 i Inputs: urls |
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 t Inputs: url |
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 a Inputs: url, fields |
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. Inputs: url, text |
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. Exam Inputs: topic, slides, language, instructions |
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。 Inputs: url, audio |
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}, Inputs: url, style, start_at, skip_first, position, text |
pdf_page_count | Count pages and report each page size of a PDF (by URL). Inputs: url |
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. Inputs: url |
pdf_watermark | Stamp diagonal text watermark on every page of a PDF (by URL). text = the watermark. Inputs: text, url |
pptx_to_pdf | PowerPoint .pptx (by URL) → PDF handout. Inputs: url |
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 Inputs: text, only |
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? Inputs: url, language |
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 li Inputs: url, lang_to, pages |
webpage_to_docx | Any article URL → Word .docx (rendered page → clean document). Inputs: url |
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 Inputs: task |
xlsx_to_pdf | Excel .xlsx (by URL) → PDF. Inputs: url |
Every block below points at https://ainetcafe.com/mcp/docs?s=registry. Pick your client and copy.
claude mcp add --transport http netcafe-docs https://ainetcafe.com/mcp/docs?s=registry
{
"mcpServers": {
"netcafe-docs": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://ainetcafe.com/mcp/docs?s=registry"]
}
}
}{
"mcpServers": {
"netcafe-docs": {
"url": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}{
"servers": {
"netcafe-docs": {
"type": "http",
"url": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}{
"context_servers": {
"netcafe-docs": {
"url": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}{
"mcpServers": {
"netcafe-docs": {
"serverUrl": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}{
"mcpServers": {
"netcafe-docs": {
"url": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}name: Netcafe Docs
version: 0.0.1
schema: v1
mcpServers:
- name: Netcafe Docs
type: streamable-http
url: https://ainetcafe.com/mcp/docs?s=registry{
"mcpServers": {
"netcafe-docs": {
"httpUrl": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}{
"mcpServers": {
"netcafe-docs": {
"type": "http",
"url": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}{
"mcpServers": {
"netcafe-docs": {
"url": "https://ainetcafe.com/mcp/docs?s=registry"
}
}
}goose://extension?url=https%3A%2F%2Fainetcafe.com%2Fmcp%2Fdocs%3Fs%3Dregistry&type=streamable_http&id=netcafe-docs&name=Netcafe%20Docs
It answered our last check on 7 November 2026 in 1348 ms. Over 11 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by ainetcafe.com and served from ainetcafe.com, the vendor's own domain: https://ainetcafe.com/mcp/docs?s=registry.
23, as returned by the server's own tools/list on 9 September 2026: check_job, check_resume, convert_to_pdf, csv_to_qbo, deep_research, doc_translate_cn, extract_invoices, extract_statement, and 15 more.
It answered our last check on 7 November 2026 in 1348 ms. Over 11 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://ainetcafe.com/mcp/docs?s=registry. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.ainetcafe. Endpoint host: ainetcafe.com. ARD identifier: urn:air:com.ainetcafe:mcp:netcafe-docs.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.