Document Extraction Hub

{
  "protocolVersion": "0.2.9",
  "name": "Document Extraction Hub",
  "description": "Pay-per-page document extraction and OCR: PDF or picture in, structured JSON out, with a source reference behind every field.",
  "url": "https://doc.halowerk.com",
  "version": "1.0.0",
  "provider": {
    "organization": "Die Netzhandwerker",
    "url": "https://netzhandwerker.de"
  },
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "skills": [
    {
      "id": "extract_document",
      "name": "extract document",
      "description": "Turn one PDF into structured JSON: header fields, tables as rows and columns, key value pairs and per page full text, each field with its page, position and confidence.",
      "tags": [
        "document-extraction",
        "pdf-to-json",
        "ocr",
        "barcode",
        "qr-code",
        "invoice-parsing",
        "table-extraction",
        "agent-tools",
        "accounting",
        "procurement",
        "archive"
      ],
      "examples": [
        "POST https://doc.halowerk.com/document"
      ]
    },
    {
      "id": "ocr_read",
      "name": "ocr read",
      "description": "Read a picture, a scan or a screenshot: full text in reading order, typed blocks with their box on the page, tables as a matrix plus markdown, and every QR code and barcode with its decoded content.",
      "tags": [
        "document-extraction",
        "pdf-to-json",
        "ocr",
        "barcode",
        "qr-code",
        "invoice-parsing",
        "table-extraction",
        "agent-tools",
        "accounting",
        "procurement",
        "archive"
      ],
      "examples": [
        "POST https://doc.halowerk.com/ocr"
      ]
    }
  ],
  "x402": {
    "enabled": true,
    "manifest": "https://doc.halowerk.com/.well-known/x402",
    "pricing": "per page"
  }
}