AI agents invoke launch_app to trigger actions in Mac Apps Launcher. 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 applications is an Execute-class action because it triggers external system operations. Severity is high due to the blast radius: an agent could be tricked into launching malicious applications, system tools with destructive capabilities (like rm, dd), or applications that expose sensitive data or compromise system security.
From the tool's definition The tool "launch_app" with description "Launch a Mac application by name" directly triggers execution of arbitrary applications on the macOS system.
Documented attack patterns abuse exactly the kind of access launch_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mac Apps Launcher, and nothing reaches the server without passing your rules. This is the rule we recommend for launch_app:
{
"version": "1",
"default": "deny",
"tools": {
"launch_app": {
"limits": [
{
"counter": "launch_app_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}launch_app 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 Mac application by name. It is categorised as a Execute tool in the Mac Apps Launcher MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mac Apps Launcher MCP server in PolicyLayer and add a rule for launch_app: 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 Mac Apps Launcher. Nothing to install.
launch_app 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_app 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_app. 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_app is provided by the Mac Apps Launcher MCP server (joshuarileydev/mac-apps-launcher). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mac Apps Launcher, 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.
3 Mac Apps Launcher tools catalogued and risk-classified — across an index of 43,000+ MCP servers.