Scroll the page up or down by a specified amount
AI agents invoke safari_scroll to trigger actions in Safari. 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 action (scrolling) that triggers an external operation in the Safari browser. While scrolling has minimal blast radius, it is an executed browser action with side effects (changing viewport position), fitting the Execute category. It does not read, write, or delete data, nor does it have financial implications.
From the tool's definition Scroll the page up or down by a specified amount
Documented attack patterns abuse exactly the kind of access safari_scroll gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Safari, and nothing reaches the server without passing your rules. This is the rule we recommend for safari_scroll:
{
"version": "1",
"default": "deny",
"tools": {
"safari_scroll": {
"limits": [
{
"counter": "safari_scroll_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}safari_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.
Scroll the page up or down by a specified amount. It is categorised as a Execute tool in the Safari MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Safari MCP server in PolicyLayer and add a rule for safari_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 Safari. Nothing to install.
safari_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 safari_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 safari_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.
safari_scroll is provided by the Safari MCP server (safari-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Safari, 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.
91 Safari tools catalogued and risk-classified — across an index of 43,000+ MCP servers.