AI agents invoke scroll_down to trigger actions in Chrome Debug MCP Server. 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.
This tool performs a browser automation action (scrolling the page), which is an Execute-category operation. It triggers an external operation (UI interaction in Chrome via debug port). The blast radius is low as scrolling has minimal harmful side effects, but it is still an active browser manipulation rather than a passive read.
From the tool's definition scroll_down — 'scroll page down one viewport height'; browser automation action that manipulates the browser state
Documented attack patterns abuse exactly the kind of access scroll_down gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chrome Debug MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for scroll_down:
{
"version": "1",
"default": "deny",
"tools": {
"scroll_down": {
"limits": [
{
"counter": "scroll_down_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scroll_down 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.
向下滚动页面一个视口高度. It is categorised as a Execute tool in the Chrome Debug MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Debug MCP Server MCP server in PolicyLayer and add a rule for scroll_down: 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 Debug MCP Server. Nothing to install.
scroll_down 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_down 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_down. 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_down is provided by the Chrome Debug MCP Server MCP server (rainmen-xia/chrome-debug-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Chrome Debug MCP Server, 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 Debug MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.