Scroll the current page or a referenced element; directions: up/down/top/bottom. amount controls pixel distance for up/down. Returns: (1) shortened YAML snapshot text, (2) base64 PNG screenshot, (3) base64 PNG screenshot with refs. Note: Snapshot is shortened by default. If you see an element in ...
AI agents use browser_scroll to create or update resources in Search — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Search environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
amount | number | — | Pixels to scroll for up/down (default 500). Ignored for top/bottom. |
target | string | — | Optional snapshot ref (e.g., 's1e5' for main frame or 's1f2e10' for iframe elements) to scroll a specific element instead of the page |
direction | string | Yes | Scroll direction/position for the current page or element |
Parameters from the server's own tool schema.
An AI agent can call browser_scroll faster than any human can review — one bad instruction and it creates or modifies resources in Search by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Scroll the current page or a referenced element; directions: up/down/top/bottom. amount controls pixel distance for up/down. Returns: (1) shortened YAML snapshot text, (2) base64 PNG screenshot, (3) base64 PNG screenshot with refs. Note: Snapshot is shortened by default. If you see an element in the screenshot that has no ref in the snapshot, call browser_snapshot with detail='all' to get the full snapshot. Warning: Snapshot may not reflect latest page state due to async web content; call browser_snapshot to get current state if needed. It is categorised as a Write tool in the Search MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
browser_scroll accepts 3 parameters: amount, target, direction. Required: direction. The full parameter table on this page comes from the server's own tool schema.
Register the Search MCP server in PolicyLayer and add a rule for browser_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 Search. Nothing to install.
browser_scroll is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the browser_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 browser_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.
browser_scroll is provided by the Search MCP server (search-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →