terminal_launch · Terminal Control MCP: Risk & Policy

WHAT IT DOES

What terminal_launch does on Terminal Control MCP

AI agents invoke terminal_launch to trigger actions in Terminal Control MCP. 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_launch needs a policy

The tool launches terminal processes in a controlled environment (virtual X11 display). While the description is empty, the context from sibling tools (terminal_capture, terminal_input, terminal_close) and server purpose clarifies this initiates execution. Terminal launches can run arbitrary commands with unpredictable side effects depending on what is subsequently executed.

From the tool's definition Server description states it 'Enables AI agents to interact with terminal-based TUI applications' and 'simulating keyboard input' combined with tool name 'terminal_launch' which launches a terminal process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

terminal_launch Rate-limited

terminal_launch 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_launch": {
      "limits": [
        {
          "counter": "terminal_launch_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 Terminal Control MCP, so you can run agents against it safely.

FAQ

Questions about terminal_launch

What does the terminal_launch tool do? +

terminal_launch. It is categorised as a Execute tool in the Terminal Control MCP 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_launch? +

Register the Terminal Control MCP server in PolicyLayer and add a rule for terminal_launch: 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 Terminal Control MCP. Nothing to install.

What risk level is terminal_launch? +

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

Can I rate-limit terminal_launch? +

Yes. Add a rate_limit block to the terminal_launch 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_launch completely? +

Set action: deny in the PolicyLayer policy for terminal_launch. 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_launch? +

terminal_launch is provided by the Terminal Control MCP server (taskhub-sh/terminal-driver-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.