ocr_image
Extract text from one or more images using OCR while preserving original line breaks. Process images locally for private, on-device data handling.
Instructions
提取一张或多张图片中的所有文字(OCR),按原始排版分行输出
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"image_paths": "<image_paths>"
},
"name": "ocr_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image_paths | Yes | 图片路径列表(绝对路径,或相对 MCP server 工作目录;支持 ~ 开头),可传多张 |