read_image_ocr_text

What read_image_ocr_text does on Nodebench

AI agents call read_image_ocr_text to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why read_image_ocr_text is rated Low

This is a pure read operation that retrieves optical character recognition data from image files. It modifies nothing, deletes nothing, executes no external commands or code, and involves no financial transactions. The local-only processing and lack of network access further confirm it has no external side effects. Low severity because misuse would only expose text content already present in provided images.

From the tool's definition Tool performs text extraction from local images using OCR (tesseract.js) with no network operations. The verb 'extract' and description 'no network' and 'deterministic' indicate it retrieves/queries data without side effects.

The rule that runs read_image_ocr_text safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read_image_ocr_text, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_image_ocr_text": {}
  }
}

Questions about read_image_ocr_text