Scrolls the page. Use x,y coordinates OR selector to scroll into view.
AI agents invoke scroll to trigger actions in Chrome MCP Docker. 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.
Scrolling is a browser interaction/execution action that manipulates the browser state. While it has minimal blast radius on its own, it is an external operation performed on a live browser session. It does not read, write, or delete data, but executes a UI interaction.
From the tool's definition 'Scrolls the page' — triggers a browser action (scrolling) via DevTools Protocol, using coordinates or element selectors
Documented attack patterns abuse exactly the kind of access scroll gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chrome MCP Docker, and nothing reaches the server without passing your rules. This is the rule we recommend for scroll:
{
"version": "1",
"default": "deny",
"tools": {
"scroll": {
"limits": [
{
"counter": "scroll_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scroll 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.
Free to start. No card required.
Scrolls the page. Use x,y coordinates OR selector to scroll into view. It is categorised as a Execute tool in the Chrome MCP Docker MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome MCP Docker MCP server in PolicyLayer and add a rule for scroll: 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 Chrome MCP Docker. Nothing to install.
scroll 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 scroll 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 scroll. 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.
scroll is provided by the Chrome MCP Docker MCP server (null-runner/chrome-mcp-docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Chrome MCP Docker, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Chrome MCP Docker tools catalogued and risk-classified — across an index of 43,000+ MCP servers.