AI agents invoke app_launch to trigger actions in ScreenHand. 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.
app_launch executes system operations (application spawning) whose effects depend on which bundle ID is supplied. This is irreversible runtime behavior that can start any installed application, potentially with side effects (opening files, running background services, executing initialization code). It does not merely read or query data, nor does it create/modify user files reversibly.
From the tool's definition Tool launches applications by bundle ID on macOS/Windows—a direct execution action that triggers external processes.
Documented attack patterns abuse exactly the kind of access app_launch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for app_launch:
{
"version": "1",
"default": "deny",
"tools": {
"app_launch": {
"limits": [
{
"counter": "app_launch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}app_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 macOS/Windows application by bundle ID (e.g.,. It is categorised as a Execute tool in the ScreenHand MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScreenHand MCP server in PolicyLayer and add a rule for app_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 ScreenHand. Nothing to install.
app_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 app_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 app_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.
app_launch is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, 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.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.