netcafe-docs

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.

{
  "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"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to redact."
    },
    "only": {
      "type": "string",
      "description": "Optional comma-separated subset, e.g. \"EMAIL,API_KEY,PRIVATE_KEY\"."
    }
  },
  "required": [
    "text"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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.

{
  "type": "object",
  "properties": {
    "csv": {
      "type": "string",
      "description": "CSV content with a header row."
    },
    "url": {
      "type": "string",
      "description": "Or a link to the CSV."
    },
    "account_id": {
      "type": "string",
      "description": "Your account number as the accounting software expects it."
    },
    "bank_id": {
      "type": "string",
      "description": "Routing / bank identifier, if your import asks for one."
    },
    "currency": {
      "type": "string",
      "description": "Three-letter currency code, default USD."
    }
  },
  "required": []
}

{
  "type": "object",
  "additionalProperties": true
}

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.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public URL of the resume (PDF or .docx)."
    }
  },
  "required": [
    "url"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public URL of the PDF, or of a page image (png/jpg) for scanned documents."
    }
  },
  "required": [
    "url"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public URL of the PDF."
    },
    "fields": {
      "type": "string",
      "description": "Optional comma-separated target columns, e.g. \"invoice_no,supplier,date,amount\". Omit to infer from the header."
    }
  },
  "required": [
    "url"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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).

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public URL of the statement PDF."
    }
  },
  "required": [
    "url"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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.

{
  "type": "object",
  "properties": {
    "urls": {
      "type": "string",
      "description": "Invoice URLs — comma-separated, or pass an array. Up to 20 per call."
    }
  },
  "required": [
    "urls"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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}".

{
  "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"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public URL of the CSV."
    },
    "text": {
      "type": "string",
      "description": "Or paste the CSV content directly."
    }
  },
  "required": []
}

{
  "type": "object",
  "additionalProperties": true
}

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>

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public URL of the audio file (mp3/wav/m4a/ogg, ≤15 MB)."
    },
    "language": {
      "type": "string",
      "description": "Hint language code like \"zh\", \"en\"; default auto-detect."
    }
  },
  "required": [
    "url"
  ]
}

{
  "type": "object",
  "additionalProperties": true
}

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

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Page URL to convert (either url or html is required)."
    },
    "html": {
      "type": "string",
      "description": "Raw HTML to convert (alternative to url)."
    }
  }
}

{
  "type": "object",
  "additionalProperties": true
}

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

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "The research question. Phrase it as a question, not a keyword."
    },
    "depth": {
      "type": "string",
      "enum": [
        "quick",
        "standard"
      ],
      "description": "quick = outline only (~1 min); standard = full cited report (~3 min). Default standard."
    }
  },
  "required": [
    "topic"
  ]
}

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "status": {
      "type": "string"
    },
    "poll_interval_seconds": {
      "type": "integer"
    }
  },
  "required": [
    "job_id",
    "status"
  ]
}

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>

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The job_id returned when the task was started."
    }
  },
  "required": [
    "job_id"
  ]
}

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "kind": {
      "type": "string"
    },
    "status": {
      "type": "string"
    },
    "is_terminal": {
      "type": "boolean"
    },
    "retry_after_seconds": {
      "type": "integer"
    },
    "next_action": {
      "type": [
        "object",
        "null"
      ]
    },
    "result": {},
    "structured_result": {},
    "error": {
      "type": "string"
    }
  },
  "required": [
    "job_id",
    "status"
  ]
}

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

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Direct URL to the PDF (e.g. an arXiv PDF link)."
    },
    "lang_to": {
      "type": "string",
      "description": "Target language, e.g. \"Simplified Chinese\", \"Japanese\". Default Simplified Chinese."
    },
    "pages": {
      "type": "string",
      "enum": [
        "first",
        "first5",
        "all"
      ],
      "description": "How much to translate. first = 1 page, first5 = first 5 pages (default), all = whole document (slow and expensive)."
    }
  },
  "required": [
    "url"
  ]
}

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "status": {
      "type": "string"
    },
    "poll_interval_seconds": {
      "type": "integer"
    }
  },
  "required": [
    "job_id",
    "status"
  ]
}

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

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "The topic, or a full outline to follow."
    },
    "slides": {
      "type": "integer",
      "description": "Number of slides (default 8)."
    },
    "language": {
      "type": "string",
      "description": "Output language, e.g. \"Chinese\", \"English\". Default Chinese."
    },
    "instructions": {
      "type": "string",
      "description": "Optional extra guidance on style or emphasis."
    }
  },
  "required": [
    "topic"
  ]
}

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "status": {
      "type": "string"
    },
    "poll_interval_seconds": {
      "type": "integer"
    }
  },
  "required": [
    "job_id",
    "status"
  ]
}

Count pages and report each page size of a PDF (by URL).

{
  "type": "object",
  "properties": {
    "url": {}
  },
  "additionalProperties": true
}

Stamp diagonal text watermark on every page of a PDF (by URL). text = the watermark.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "url": {}
  },
  "additionalProperties": true
}

Excel .xlsx (by URL) → PDF.

{
  "type": "object",
  "properties": {
    "url": {}
  },
  "additionalProperties": true
}

PowerPoint .pptx (by URL) → PDF handout.

{
  "type": "object",
  "properties": {
    "url": {}
  },
  "additionalProperties": true
}

Any article URL → Word .docx (rendered page → clean document).

{
  "type": "object",
  "properties": {
    "url": {}
  },
  "additionalProperties": true
}

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。

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string"
    },
    "audio": {}
  },
  "additionalProperties": true
}

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。

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "url": {},
    "target": {
      "type": "string"
    }
  },
  "additionalProperties": true
}