AI agents call browser_list_tabs to retrieve information from Byob without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query operation that retrieves and displays information about existing browser state. It does not modify, delete, execute code, or trigger any actions—it simply enumerates open tabs. While it could reveal sensitive information in URLs or titles (information disclosure risk), the functional category is Read.
From the tool's definition Tool 'browser_list_tabs' returns metadata (id, url, title, active flag, windowId) about open tabs with no side effects or modifications.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Returns id, url, title, active flag, and windowId for every open tab. It is categorised as a Read tool in the Byob MCP Server, which means it retrieves data without modifying state.
Register the Byob MCP server in PolicyLayer and add a rule for browser_list_tabs: 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 Byob. Nothing to install.
browser_list_tabs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_list_tabs 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_list_tabs. 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_list_tabs is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.