resize_shell · Interactive Shell MCP: Risk & Policy

WHAT IT DOES

What resize_shell does on Interactive Shell MCP

AI agents invoke resize_shell to trigger actions in Interactive Shell 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 resize_shell needs a policy

This tool modifies the terminal dimensions (rows/columns) of an active PTY session. While not directly executing commands or destroying data, it triggers an external operation (SIGWINCH signal) on a running process and changes the state of an active shell session. It's more than a read, and closest to Execute as it affects a running process's environment.

From the tool's definition Resize the terminal of an active shell session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

resize_shell Rate-limited

resize_shell 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": {
    "resize_shell": {
      "limits": [
        {
          "counter": "resize_shell_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 Interactive Shell MCP, so you can run agents against it safely.

FAQ

Questions about resize_shell

What does the resize_shell tool do? +

Resize the terminal of an active shell session. It is categorised as a Execute tool in the Interactive Shell 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 resize_shell? +

Register the Interactive Shell MCP server in PolicyLayer and add a rule for resize_shell: 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 Interactive Shell MCP. Nothing to install.

What risk level is resize_shell? +

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

Can I rate-limit resize_shell? +

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

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

resize_shell is provided by the Interactive Shell MCP server (lightos/interactive-shell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.