Wait for a condition in the browser (selector, text, URL, load state).
AI agents invoke cmux_browser_wait 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.
cmux_browser_wait is an Execute-category tool because it triggers browser monitoring/control operations on external instances, even though the wait itself is passive. The risk arises when combined with sibling tools for orchestrated browser automation: an AI agent could misuse this to wait for malicious page states, exfiltrate data, or coordinate timing for harmful actions (e.g., waiting for a confirmation dialog…
From the tool's definition Tool description states it 'Wait[s] for a condition in the browser' by monitoring selectors, text, URL, and load state. The sibling tools (cmux_browser_click, cmux_browser_eval, cmux_browser_fill, cmux_browser_navigate) all perform browser automation actions.
Documented attack patterns abuse exactly the kind of access cmux_browser_wait 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_wait:
{
"version": "1",
"default": "deny",
"tools": {
"cmux_browser_wait": {
"limits": [
{
"counter": "cmux_browser_wait_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cmux_browser_wait 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.
Wait for a condition in the browser (selector, text, URL, load state). 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_wait: 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_wait 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_wait 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_wait. 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_wait 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.