Scroll up/down. Stealth: jittered steps. Fast: instant.
AI agents invoke chrome_scroll to trigger actions in Chrome MCP Stealth. 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.
chrome_scroll triggers a browser action (scrolling) within an automated browser session. It executes an interaction against a live browser, which can affect page state (e.g., triggering lazy-loaded content, infinite scroll, or dynamic DOM changes). While scrolling itself is relatively benign, as part of a stealth automation suite it contributes to browser-based execution flows.
From the tool's definition Scroll up/down. Stealth: jittered steps. Fast: instant.
Attacks that exploit this kind of access
Scroll up/down. Stealth: jittered steps. Fast: instant. It is categorised as a Execute tool in the Chrome MCP Stealth MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome MCP Stealth MCP server in PolicyLayer and add a rule for chrome_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 Stealth. Nothing to install.
chrome_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 chrome_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 chrome_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.
chrome_scroll is provided by the Chrome MCP Stealth MCP server (riaan-fourie/chrome-mcp-stealth). 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 →