start_shell_session · Interactive Shell MCP: Risk & Policy

WHAT IT DOES

What start_shell_session does on Interactive Shell MCP

AI agents invoke start_shell_session 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 start_shell_session needs a policy

Creating a persistent shell session grants the ability to execute arbitrary commands and run external operations whose effects depend entirely on what commands an agent chooses to send to the shell. The PTY/terminal emulation support indicates full interactive shell access.

From the tool's definition Tool spawns a new PTY shell with full terminal emulation. Server description states it 'Enables LLMs to create and manage persistent, interactive shell sessions' and 'allows for sequential command execution'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_shell_session Rate-limited

start_shell_session 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": {
    "start_shell_session": {
      "limits": [
        {
          "counter": "start_shell_session_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 start_shell_session

What does the start_shell_session tool do? +

Spawns a new PTY shell with a virtual terminal emulator and returns a unique session ID. 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 start_shell_session? +

Register the Interactive Shell MCP server in PolicyLayer and add a rule for start_shell_session: 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 start_shell_session? +

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

Can I rate-limit start_shell_session? +

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

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

start_shell_session 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.