Summarize your unread channel messages: per-channel unread count, mention-unread count (messages that @-mention you), your cursor (lastReadSeq), the channel head seq, and trimmedBeforeCursor (messages lost to retention before you read them — never silently dropped). Cheap to call; does not consum...
AI agents call channel_unread 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.
This tool retrieves metadata about unread messages without side effects. It explicitly states it 'does not consume messages' and is 'cheap to call', indicating read-only query semantics. The worst-case misuse scenario is information disclosure of channel message counts and cursor positions, which is low-severity. No write, execute, destructive, or financial operations are possible.
From the tool's definition Tool description states it 'Summarize[s] your unread channel messages' and 'does not consume messages'. The operations performed are purely informational: retrieving 'per-channel unread count', 'mention-unread count', 'cursor', 'channel head seq', and…
Attacks that exploit this kind of access
Summarize your unread channel messages: per-channel unread count, mention-unread count (messages that @-mention you), your cursor (lastReadSeq), the channel head seq, and trimmedBeforeCursor (messages lost to retention before you read them — never silently dropped). Cheap to call; does not consume messages. Follow up with channel_read + channel_ack. 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 channel_unread: 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_unread 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 channel_unread 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_unread. 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_unread 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_unread 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 →