AI agents use channel_leave to create or update resources in Wmux — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wmux environment.
Leaving a channel is a reversible write operation: the caller can rejoin or the action can be undone. It modifies membership state but causes no data loss, code execution, or financial impact. The blast radius is low—affecting only the caller's session state within the Wmux terminal multiplexer.
From the tool's definition Tool name 'channel_leave' and description 'Leave a channel' indicate a state-modifying action that removes the caller from a channel membership or session.
Attacks that exploit this kind of access
Leave a channel. The caller\. It is categorised as a Write tool in the Wmux MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wmux MCP server in PolicyLayer and add a rule for channel_leave: 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.
channel_leave is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the channel_leave 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 channel_leave. 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.
channel_leave 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.
channel_leave 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 →