start_process · Persistent Shell MCP: Risk & Policy

WHAT IT DOES

What start_process does on Persistent Shell MCP

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

This tool allows execution of arbitrary processes whose effects depend on the arguments provided (e.g., network calls, file operations, code execution). While not inherently destructive, the ability to start any process in an isolated workspace poses significant risk if an AI agent is tricked into launching malicious, resource-intensive, or unintended operations.

From the tool's definition The tool 'start_process' starts long-running or interactive processes in persistent tmux sessions. The server description explicitly states it 'enables AI assistants to execute shell commands and manage long-running processes.' This is command execution…

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 Persistent Shell 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 or interactive process. Defaults to the background. It is categorised as a Execute tool in the Persistent 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_process? +

Register the Persistent Shell 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 Persistent Shell 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 Persistent Shell MCP server (tntisdial/persistent-shell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.