create_terminal · Persistent Terminal MCP Server MCP

WHAT IT DOES

What create_terminal does on Persistent Terminal MCP Server

AI agents invoke create_terminal to trigger actions in Persistent Terminal MCP Server. 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 create_terminal needs a policy

Creating a persistent terminal session establishes an execution environment capable of running arbitrary shell commands. The terminal persists even after disconnection, which increases the blast radius as processes can continue running unattended. While the creation itself is an initialization step, its primary purpose is to enable command execution, making Execute the most appropriate category.

From the tool's definition Create a new persistent terminal session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_terminal Rate-limited

create_terminal 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": {
    "create_terminal": {
      "limits": [
        {
          "counter": "create_terminal_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 Persistent Terminal MCP Server, so you can run agents against it safely.

FAQ

Questions about create_terminal

What does the create_terminal tool do? +

Create a new persistent terminal session. It is categorised as a Execute tool in the Persistent Terminal MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_terminal? +

Register the Persistent Terminal MCP Server MCP server in PolicyLayer and add a rule for create_terminal: 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 Persistent Terminal MCP Server. Nothing to install.

What risk level is create_terminal? +

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

Can I rate-limit create_terminal? +

Yes. Add a rate_limit block to the create_terminal 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 create_terminal completely? +

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

create_terminal is provided by the Persistent Terminal MCP Server MCP server (masx200/persistent-terminal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.