document_extract_json

What document_extract_json does on Hwpx

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

Why document_extract_json is rated Low

This tool performs data retrieval and querying operations on HWPX documents, converting their content into readable formats (Markdown and JSON). It has no side effects, does not modify the source document, and does not execute arbitrary code or trigger external operations. The core function is read-only access to document content, placing it firmly in the Read category with low severity.

From the tool's definition Tool name 'document_extract_json' and description state it 'extracts Markdown and structured JSON' from local documents. The verb 'extract' indicates retrieval of data with no modification.

The rule that runs document_extract_json safely

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

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

Questions about document_extract_json