AI agents call browser_network to retrieve information from Wmux without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/queries accumulated network traffic data from a browser session. It has no side effects itself (clear=true resets the collection buffer, which is minor state management). The severity is medium because network requests may contain sensitive data like authentication tokens, API keys, or personal information that could be exfiltrated if misused.
From the tool's definition Retrieve network requests collected from the browser page
Attacks that exploit this kind of access
Retrieve network requests collected from the browser page. Requests are accumulated over time; use clear=true to reset. Use a URL glob pattern to filter. It is categorised as a Read tool in the Wmux MCP Server, which means it retrieves data without modifying state.
Register the Wmux MCP server in PolicyLayer and add a rule for browser_network: 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_network 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_network 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_network. 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_network 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_network 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 →