terminal_create · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What terminal_create does on Claude Flow

AI agents invoke terminal_create to trigger actions in Claude Flow. 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_create needs a policy

This tool creates a persistent terminal session capable of executing arbitrary shell commands across multiple turns and agents. It is an Execute-category tool because it enables running shell commands and external operations.

From the tool's definition "Create a new terminal session" and "persistent terminal session across turns/agents with output capture and replay"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

terminal_create Rate-limited

terminal_create 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_create": {
      "limits": [
        {
          "counter": "terminal_create_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about terminal_create

What does the terminal_create tool do? +

Create a new terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine. It is categorised as a Execute tool in the Claude Flow 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_create? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for terminal_create: 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 Claude Flow. Nothing to install.

What risk level is terminal_create? +

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

Can I rate-limit terminal_create? +

Yes. Add a rate_limit block to the terminal_create 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_create completely? +

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

terminal_create is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.