Return structured OSC 133 prompt/command events (prompt_start, prompt_end, command_start, command_end with exit code) from a terminal. Requires shell integration — wmux auto-injects for pwsh and bash; cmd.exe is unsupported. Use this instead of terminal_read when you need command boundaries, exit...
AI agents call terminal_read_events 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 is a read operation that retrieves terminal event metadata (prompt_start, prompt_end, command_start, command_end, exit codes). It does not create, modify, delete, or execute anything — it only observes and returns structured data about terminal state.
From the tool's definition Tool name is 'terminal_read_events' and description states 'Return structured OSC 133 prompt/command events' — it retrieves and queries terminal event data with 'no side effects' beyond observation.
Attacks that exploit this kind of access
Return structured OSC 133 prompt/command events (prompt_start, prompt_end, command_start, command_end with exit code) from a terminal. Requires shell integration — wmux auto-injects for pwsh and bash; cmd.exe is unsupported. Use this instead of terminal_read when you need command boundaries, exit codes, or byte offsets for diff-style reads. 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 terminal_read_events: 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.
terminal_read_events 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 terminal_read_events 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 terminal_read_events. 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.
terminal_read_events 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.
terminal_read_events 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 →