terminal_read

Read the current visible text from a terminal. Omit ptyId to read the active terminal. Pass tail_lines to cap the response to the last N non-empty lines (saves tokens when the full viewport is not needed). For structured command boundaries / exit codes, use terminal_read_events instead.

Server Wmux openwong2kim/wmux
Category Read
Risk class Low
Parameters 00 required

What terminal_read does on Wmux

AI agents call terminal_read 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.

Why terminal_read needs a policy

This tool retrieves and queries the current state of terminal output. It has no capability to modify, execute commands, delete data, or trigger side effects. The user must explicitly pass tail_lines to optimize token usage, indicating passive observation only. No destructive, financial, or execution capabilities are present.

From the tool's definition Tool name is 'terminal_read' and description states 'Read the current visible text from a terminal.' The verb 'read' and explicit readonly operation confirm retrieval without side effects.

Questions about terminal_read

What does the terminal_read tool do? +

Read the current visible text from a terminal. Omit ptyId to read the active terminal. Pass tail_lines to cap the response to the last N non-empty lines (saves tokens when the full viewport is not needed). For structured command boundaries / exit codes, use terminal_read_events instead. It is categorised as a Read tool in the Wmux MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on terminal_read? +

Register the Wmux MCP server in PolicyLayer and add a rule for terminal_read: 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.

What risk level is terminal_read? +

terminal_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit terminal_read? +

Yes. Add a rate_limit block to the terminal_read 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.

How do I block terminal_read completely? +

Set action: deny in the PolicyLayer policy for terminal_read. 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.

What MCP server provides terminal_read? +

terminal_read 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.

// THE FULL RECORD

terminal_read 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.