AI agents invoke cmux_wait_ready to trigger actions in Cmux. 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_wait_ready performs polling and state-dependent triggering on a terminal/browser UI. While it appears non-destructive on its surface, it executes a wait-loop that blocks until readiness criteria are satisfied, then returns results. This is fundamentally an execution operation (polling loop, conditional branching) rather than passive data retrieval.
From the tool's definition Tool polls a surface/panel and waits for readiness state, which involves monitoring and triggering on screen state changes.
Attacks that exploit this kind of access
Poll a surface/panel until it looks ready for input, then return the final screen. Ready = the screen matches. It is categorised as a Execute tool in the Cmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cmux MCP server in PolicyLayer and add a rule for cmux_wait_ready: 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. Nothing to install.
cmux_wait_ready 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_wait_ready 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_wait_ready. 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_wait_ready is provided by the Cmux MCP server (puchkoff/cmux-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →