{
  "id": "doc.ocr",
  "object": "tool",
  "name": "Searchable PDF (OCR)",
  "summary": "Text layer for scans and photos.",
  "description": "Runs OCRmyPDF (Tesseract) over a scanned PDF or a set of images and returns a searchable PDF with an invisible text layer, plus the recognised text. Supports 16 languages, deskewing, automatic page rotation and PDF/A output.",
  "category": "documents",
  "hosted_by": "Opentools",
  "runtime": "container",
  "side_effects": false,
  "status": "live",
  "credits": 4,
  "price": "$0.0040",
  "providers": [
    {
      "id": "opentools",
      "name": "Opentools",
      "price": "$0.0040"
    }
  ],
  "mcp_name": "doc_ocr",
  "input_schema": {
    "type": "object",
    "properties": {
      "files": {
        "minItems": 1,
        "maxItems": 50,
        "type": "array",
        "items": {
          "anyOf": [
            {
              "type": "object",
              "properties": {
                "url": {
                  "type": "string",
                  "format": "uri",
                  "description": "Public http(s) URL of the file"
                }
              },
              "required": [
                "url"
              ]
            },
            {
              "type": "object",
              "properties": {
                "file_id": {
                  "type": "string",
                  "format": "uuid",
                  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
                  "description": "An id returned by POST /v1/files"
                }
              },
              "required": [
                "file_id"
              ]
            },
            {
              "type": "object",
              "properties": {
                "base64": {
                  "type": "string",
                  "description": "Base64-encoded file bytes (up to 10 MB)"
                },
                "name": {
                  "type": "string",
                  "description": "File name, e.g. invoice.pdf"
                },
                "content_type": {
                  "type": "string"
                }
              },
              "required": [
                "base64",
                "name"
              ]
            },
            {
              "type": "object",
              "properties": {
                "connection": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 64,
                  "description": "A storage connection id or name (see storage.connections)"
                },
                "path": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1024,
                  "description": "Path of the file in that connection, e.g. reports/q3.pdf"
                }
              },
              "required": [
                "connection",
                "path"
              ]
            }
          ],
          "x-file": true,
          "description": "A file: { url }, { file_id }, { base64, name } or { connection, path } from connected storage"
        },
        "description": "One scanned PDF, or images (one page each, in order)"
      },
      "languages": {
        "default": [
          "eng"
        ],
        "description": "Tesseract languages, e.g. ['eng','deu']. chi_sim/chi_tra are Chinese, jpn Japanese, kor Korean.",
        "minItems": 1,
        "maxItems": 8,
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "eng",
            "deu",
            "fra",
            "spa",
            "ita",
            "por",
            "nld",
            "pol",
            "rus",
            "ukr",
            "chi_sim",
            "chi_tra",
            "jpn",
            "kor",
            "ara",
            "hin"
          ]
        }
      },
      "mode": {
        "default": "skip",
        "description": "skip pages that already have text, force OCR on every page (rasterises), or redo an existing OCR layer",
        "type": "string",
        "enum": [
          "skip",
          "force",
          "redo"
        ]
      },
      "deskew": {
        "default": false,
        "description": "Straighten crooked scans",
        "type": "boolean"
      },
      "rotate_pages": {
        "default": true,
        "description": "Fix pages scanned sideways or upside down",
        "type": "boolean"
      },
      "pdfa": {
        "default": false,
        "description": "Return PDF/A-2b for archiving",
        "type": "boolean"
      }
    },
    "required": [
      "files"
    ]
  },
  "kind": "tool"
}