crow_browser_scroll_extract
Auto-scroll an infinite-scroll / lazy-load page, collecting items each pass. Stops when no new items load or max_scrolls is hit.
This record as markdown: /tools/kh0pper-crow/crow-browser-scroll-extract.md
What crow_browser_scroll_extract does on Crow
AI agents invoke crow_browser_scroll_extract to trigger actions in Crow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why crow_browser_scroll_extract is rated High
This tool drives browser automation (scrolling, waiting for lazy-load triggers, extracting DOM content across multiple passes), which constitutes executing browser actions against external pages. While it primarily reads data, the act of programmatically controlling a browser and triggering network requests/page events places it in the Execute category, which is more severe than a passive Read.
From the tool's definition 'Auto-scroll an infinite-scroll / lazy-load page, collecting items each pass' — triggers browser actions (scrolling) and external page interactions repeatedly until a condition is met
Attacks that exploit this kind of access
The rule that runs crow_browser_scroll_extract 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_scroll_extract, this is the rule to start with:
crow_browser_scroll_extract stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every crow_browser_scroll_extract call is checked against it from then on.
Questions about crow_browser_scroll_extract
Auto-scroll an infinite-scroll / lazy-load page, collecting items each pass. Stops when no new items load or max_scrolls is hit. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for crow_browser_scroll_extract: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crow. Nothing to install.
crow_browser_scroll_extract is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the crow_browser_scroll_extract rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for crow_browser_scroll_extract. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
crow_browser_scroll_extract is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crow, and thousands of servers like it.
This server
Across the catalogue