terminal_send_key · Wmux MCP: Risk & Policy

WHAT IT DOES

What terminal_send_key does on Wmux

AI agents invoke terminal_send_key to trigger actions in Wmux. 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.

WHY IT NEEDS A POLICY

Why terminal_send_key needs a policy

Sending keys to a terminal can trigger arbitrary command execution, confirm prompts, interrupt processes, or manipulate running programs. This is an Execute-level action because the effects depend entirely on what is running in the terminal at the time. Misuse could run destructive commands or confirm dangerous prompts, making severity high.

From the tool's definition 'Send a named key to a terminal' — directly sends input/keystrokes to a terminal process (PTY), triggering execution of whatever is running in that terminal

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

terminal_send_key Rate-limited

terminal_send_key stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "terminal_send_key": {
      "limits": [
        {
          "counter": "terminal_send_key_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Wmux, so you can run agents against it safely.

FAQ

Questions about terminal_send_key

What does the terminal_send_key tool do? +

Send a named key to a terminal. Omit ptyId to target the active terminal. Use surface_list() to discover available PTY IDs. It is categorised as a Execute tool in the Wmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on terminal_send_key? +

Register the Wmux MCP server in PolicyLayer and add a rule for terminal_send_key: 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_send_key? +

terminal_send_key is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit terminal_send_key? +

Yes. Add a rate_limit block to the terminal_send_key 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_send_key completely? +

Set action: deny in the PolicyLayer policy for terminal_send_key. 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_send_key? +

terminal_send_key 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.