start_process · Terminally MCP: Risk & Policy

WHAT IT DOES

What start_process does on Terminally MCP

AI agents invoke start_process to trigger actions in Terminally 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_process needs a policy

This tool runs external processes/code execution, making it an Execute category risk. Severity is high because even in an isolated tmux environment, a malicious AI agent could execute harmful commands (resource exhaustion, data exfiltration from the sandbox, or lateral attacks). The 'returns immediately' behavior combined with 'logs stream' suggests async execution that could be harder to monitor.

From the tool's definition The tool 'start_process' executes commands in a terminal environment ('long-running process'), with effects determined entirely by the command argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_process Rate-limited

start_process 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_process": {
      "limits": [
        {
          "counter": "start_process_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 Terminally MCP, so you can run agents against it safely.

FAQ

Questions about start_process

What does the start_process tool do? +

Start a long-running process; returns immediately; logs stream to pipe-pane file. It is categorised as a Execute tool in the Terminally 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_process? +

Register the Terminally MCP server in PolicyLayer and add a rule for start_process: 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 Terminally MCP. Nothing to install.

What risk level is start_process? +

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

Can I rate-limit start_process? +

Yes. Add a rate_limit block to the start_process 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_process completely? +

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

start_process is provided by the Terminally MCP server (nighttrek/terminally-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.