AI agents call browser_console 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.
The tool reads/retrieves console messages from the browser page. The primary action is fetching already-collected data with no side effects, making it a Read operation. The optional clear=true flag could reset the buffer, but the core function is data retrieval. Medium severity because console messages may contain sensitive information like tokens, credentials, or application state.
From the tool's definition Retrieve console messages collected from the browser page. Messages are accumulated over time
Attacks that exploit this kind of access
Retrieve console messages collected from the browser page. Messages are accumulated over time; use clear=true to reset. 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_console: 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_console 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_console 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_console. 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_console 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_console 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 →