AI agents invoke cmux_browser_console to trigger actions in Cmux Agent. 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.
The tool can both retrieve and clear browser console logs. The 'clear' action is a destructive side-effect on browser session state (console history cannot be recovered once cleared), but the blast radius is limited to ephemeral console data. Per severity rules, the most severe applicable category wins; clearing browser state is a Execute-level action (modifying runtime environment).
From the tool's definition 'Get or clear browser console logs/errors' — the 'clear' action modifies browser state (irreversibly removes console history), while 'get' is a read operation. The clearing side-effect elevates this beyond pure Read.
Documented attack patterns abuse exactly the kind of access cmux_browser_console gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cmux Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for cmux_browser_console:
{
"version": "1",
"default": "deny",
"tools": {
"cmux_browser_console": {
"limits": [
{
"counter": "cmux_browser_console_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cmux_browser_console stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get or clear browser console logs/errors. It is categorised as a Execute tool in the Cmux Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cmux Agent MCP server in PolicyLayer and add a rule for cmux_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 Cmux Agent. Nothing to install.
cmux_browser_console 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 cmux_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 cmux_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.
cmux_browser_console is provided by the Cmux Agent MCP server (multiagentcognition/cmux-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cmux Agent, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
63 Cmux Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.