terminal-start · TermSSH MCP: Risk & Policy

WHAT IT DOES

What terminal-start does on TermSSH MCP

AI agents invoke terminal-start to trigger actions in TermSSH 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-start needs a policy

Starting an interactive terminal session grants the ability to execute arbitrary shell commands on a remote server. This is a classic Execute operation with critical severity because: (1) blast radius is maximal—any command the remote user can run is now available to the AI agent, (2) combined with sibling tools like terminal-write and terminal-read, an agent can fully automate remote compromise, lateral movement,…

From the tool's definition Tool description states 'Start an interactive terminal session on the remote SSH server', enabling execution of arbitrary commands on remote systems. The sibling tool 'terminal-write' and context of 'stateful workflows' confirm this permits command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

terminal-start Rate-limited

terminal-start 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-start": {
      "limits": [
        {
          "counter": "terminal-start_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 TermSSH MCP, so you can run agents against it safely.

FAQ

Questions about terminal-start

What does the terminal-start tool do? +

Start an interactive terminal session on the remote SSH server. Reuses a managed session by default unless multiSession is true. It is categorised as a Execute tool in the TermSSH 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-start? +

Register the TermSSH MCP server in PolicyLayer and add a rule for terminal-start: 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 TermSSH MCP. Nothing to install.

What risk level is terminal-start? +

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

Can I rate-limit terminal-start? +

Yes. Add a rate_limit block to the terminal-start 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-start completely? +

Set action: deny in the PolicyLayer policy for terminal-start. 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-start? +

terminal-start is provided by the TermSSH MCP server (rayss868/termssh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.