# com.ainetcafe/netcafe-docs

> Statements, invoices, tables, ledgers — every result carries its own arithmetic proof.

- name: com.ainetcafe/netcafe-docs
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 88/100 flags: duplicate-repo
- quality: 94/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.ainetcafe%2Fnetcafe-docs
- tools: https://api.protogrid.dev/v1/servers/com.ainetcafe%2Fnetcafe-docs/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "netcafe-docs": {
      "type": "http",
      "url": "https://ainetcafe.com/mcp/docs?s=registry"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-95% ~updated-57d-ago -duplicate-repo(13 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (strong)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- warn `tools.annotations`: only 16 of 23 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 16 of 23 tools declare all four hints; missing: pdf_page_count (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); pptx_to_pdf (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); doc_translate_cn (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 3,158 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 23, about 3,158 tokens to load them all
- tool set hash: d00c33d46c2ea9a99566c4ccc413a541
- badge: [![protogrid quality](https://protogrid.dev/badge/com.ainetcafe/netcafe-docs.svg)](https://protogrid.dev/servers/com.ainetcafe/netcafe-docs)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://ainetcafe.com/mcp/docs?s=registry (streamable-http, auth none, reachable true, uptime30d 0.9480519)

## Packages

_none_

## Tools (23)

- `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 — GET https://ainetcafe.com/t/check_job?job_id=<id-from-a-job-tool>
- `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 resumes.
- `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
- `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.
- `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. 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
- `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。
- `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 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.
- `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 you know whether the table is safe to use for accounting. Text-layer PDFs only (scanned images not yet supported).
- `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-layer PDFs only.
- `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.
- `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":"Q3 review","slides":8} → poll check_job
- `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。
- `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}".
- `pdf_page_count`: Count pages and report each page size of a PDF (by 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.
- `pdf_watermark`: Stamp diagonal text watermark on every page of a PDF (by URL). text = the watermark.
- `pptx_to_pdf`: PowerPoint .pptx (by URL) → PDF handout.
- `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 the answer can be restored.
- `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>
- `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-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
- `webpage_to_docx`: Any article URL → Word .docx (rendered page → clean document).
- `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 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.
- `xlsx_to_pdf`: Excel .xlsx (by URL) → PDF.