Image to Text OCR for Gemini CLI

io.github.sumitrmardy/image-to-text-ocr

OCR text from image URLs, 30 languages, lines with boxes. One flat row per image. Billed on text.

client:Gemini CLI transport:streamable-http

Install Image to Text OCR in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

{
  "mcpServers": {
    "image-to-text-ocr": {
      "httpUrl": "https://mcp.apify.com/?tools=sumitr_mardy/image-to-text-ocr"
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs