AI agents invoke browser_tabs to trigger actions in Wmux. 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 browser automation actions (open, select, close tabs) that trigger external operations in a browser. While listing is a read operation, the ability to open new tabs (which could navigate to URLs) and close tabs makes this Execute-level. The most severe applicable action is opening/closing tabs which constitutes triggering external browser operations.
From the tool's definition Manage browser tabs: list all tabs, open a new tab, select a tab, or close a tab
Attacks that exploit this kind of access
Manage browser tabs: list all tabs, open a new tab, select a tab, or close a tab. It is categorised as a Execute tool in the Wmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Wmux MCP server in PolicyLayer and add a rule for browser_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 Wmux. Nothing to install.
browser_tabs 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_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_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_tabs is provided by the Wmux MCP server (openwong2kim/wmux). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
browser_tabs is one line of Wmux's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →