Restart the Selenium browser session.
AI agents invoke browser_reset to trigger actions in SeleniumMCP. 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.
Restarting a browser session is an operational action that terminates the current session and starts a new one. This is an Execute-level action as it triggers an external operation (browser session management). While it discards the current session state (cookies, open tabs, etc.), it is not truly irreversible data destruction in the Destructive sense — the browser itself is restarted, not data permanently deleted.
From the tool's definition Restart the Selenium browser session
Attacks that exploit this kind of access
Restart the Selenium browser session. It is categorised as a Execute tool in the SeleniumMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Selenium MCP server in PolicyLayer and add a rule for browser_reset: 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 SeleniumMCP. Nothing to install.
browser_reset 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 browser_reset 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_reset. 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_reset is provided by the Selenium MCP server (lokii0911/seleniummcp). 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 →