AI agents invoke spawn_process to trigger actions in Interactive Terminal 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.
Spawning an interactive CLI process is an Execute-category action with critical severity. It can launch arbitrary processes (shells, SSH sessions, REPLs, debuggers), giving an AI agent persistent, stateful access to system resources. This is a foundational capability that enables virtually any subsequent action — including destructive or financial operations — making misuse catastrophic in blast radius.
From the tool's definition 'Spawns a new interactive CLI process' — the server description explicitly mentions spawning persistent processes like SSH sessions, debuggers, and REPLs with continuous input/output interaction.
Documented attack patterns abuse exactly the kind of access spawn_process gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Interactive Terminal MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for spawn_process:
{
"version": "1",
"default": "deny",
"tools": {
"spawn_process": {
"limits": [
{
"counter": "spawn_process_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}spawn_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.
Free to start. No card required.
Spawns a new interactive CLI process. It is categorised as a Execute tool in the Interactive Terminal MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Interactive Terminal MCP server in PolicyLayer and add a rule for spawn_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 Interactive Terminal MCP. Nothing to install.
spawn_process is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the spawn_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.
Set action: deny in the PolicyLayer policy for spawn_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.
spawn_process is provided by the Interactive Terminal MCP server (wangyihang/interactive-terminal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Interactive Terminal MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Interactive Terminal MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.