scan_document

What scan_document does on Iconnect

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

Why scan_document is rated Low

The tool extracts information from an image using OCR, which is a passive data retrieval operation with no side effects, state changes, or ability to modify or destroy data. It falls clearly into the Read category. Severity is low because extraction of text from local images has minimal blast radius — no financial, destructive, or execution capabilities are involved.

From the tool's definition Tool description states 'Extract text and structure from an image file' — this is a read-only operation that retrieves and processes data without modifying, deleting, or executing external operations. The Vision framework OCR performs analysis only.

The rule that runs scan_document safely

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

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

Questions about scan_document