crow_browser_paginate

What crow_browser_paginate does on Crow

AI agents call crow_browser_paginate 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_paginate is rated Low

This tool retrieves and aggregates paginated content without side effects. It performs navigation and content collection, which are Read operations. The low severity reflects minimal blast radius: misuse would only expose existing data already accessible through the pagination interface, not modify systems, execute code, or cause irreversible damage.

From the tool's definition Tool description states it 'Follow pagination links and collect content from multiple pages. Returns combined results' — operations are read-only data retrieval with no modification, deletion, or execution of external commands.

The rule that runs crow_browser_paginate 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_paginate, this is the rule to start with:

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

Questions about crow_browser_paginate