Launch a TUI application in a managed pseudo-terminal. Returns a session ID for subsequent interactions.
AI agents invoke launch to trigger actions in Tui. 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.
Launching arbitrary TUI applications constitutes code execution in a terminal environment. While not inherently destructive, the blast radius is high because an AI agent could launch malicious applications, background processes, resource-intensive operations, or tools that interact with sensitive system components. The agent gains a new session ID for subsequent control over the spawned process, amplifying the risk.
From the tool's definition Tool description states 'Launch a TUI application in a managed pseudo-terminal', which executes arbitrary terminal applications.
Documented attack patterns abuse exactly the kind of access launch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tui, and nothing reaches the server without passing your rules. This is the rule we recommend for launch:
{
"version": "1",
"default": "deny",
"tools": {
"launch": {
"limits": [
{
"counter": "launch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}launch 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.
Launch a TUI application in a managed pseudo-terminal. Returns a session ID for subsequent interactions. It is categorised as a Execute tool in the Tui MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tui MCP server in PolicyLayer and add a rule for launch: 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 Tui. Nothing to install.
launch 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 launch 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 launch. 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.
launch is provided by the Tui MCP server (nvms/tui-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tui, 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.
13 Tui tools catalogued and risk-classified — across an index of 43,000+ MCP servers.