{
  "id": "image.ocr",
  "object": "tool",
  "name": "Read text in image",
  "summary": "OCR to text, hOCR or boxes.",
  "description": "Reads the text in a photo, screenshot or scan with Tesseract. Returns plain text, hOCR (HTML with positions) or TSV with a bounding box and confidence for every word.",
  "category": "images",
  "hosted_by": "Opentools",
  "runtime": "container",
  "side_effects": false,
  "status": "live",
  "credits": 2,
  "price": "$0.0020",
  "providers": [
    {
      "id": "opentools",
      "name": "Opentools",
      "price": "$0.0020"
    }
  ],
  "mcp_name": "image_ocr",
  "input_schema": {
    "type": "object",
    "properties": {
      "file": {
        "anyOf": [
          {
            "type": "object",
            "properties": {
              "url": {
                "type": "string",
                "format": "uri",
                "description": "Public http(s) URL of the file"
              }
            },
            "required": [
              "url"
            ]
          },
          {
            "type": "object",
            "properties": {
              "file_id": {
                "type": "string",
                "format": "uuid",
                "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
                "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": "The image"
      },
      "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"
          ]
        }
      },
      "format": {
        "default": "txt",
        "description": "Output: text, hOCR, or TSV word boxes",
        "type": "string",
        "enum": [
          "txt",
          "hocr",
          "tsv"
        ]
      },
      "psm": {
        "default": 3,
        "description": "Tesseract page segmentation mode (3 automatic, 6 one block, 7 one line, 11 sparse text)",
        "type": "integer",
        "minimum": 0,
        "maximum": 13
      }
    },
    "required": [
      "file"
    ]
  },
  "kind": "tool"
}