crow_browser_extract_tables

What crow_browser_extract_tables does on Crow

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

Why crow_browser_extract_tables is rated Low

This tool reads and parses DOM content (HTML tables) from a web page and returns it as structured data. It performs data extraction only, with no side effects. There is no creation, modification, deletion, or execution of arbitrary code. The worst-case misuse would be exfiltration of visible table data on the current page, which is a read-only concern with limited blast radius. Classified as Read with low severity.

From the tool's definition Tool name and description indicate it 'Extract[s] HTML tables from the current page as structured JSON data' — a retrieval operation with no modification, deletion, or execution of external commands.

The rule that runs crow_browser_extract_tables safely

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

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

Questions about crow_browser_extract_tables