Launch a previously built macOS application by its bundle path or target label.
AI agents invoke bazel_macos_launch to trigger actions in XcodeBazelMCP. 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 an application is an Execute-category action because it runs compiled code whose behavior depends on the application being launched and its arguments/environment. While the application was previously built, the launch action itself triggers execution of arbitrary code.
From the tool's definition Tool 'bazel_macos_launch' performs the action of launching a macOS application, which is an external operation that executes code and triggers runtime behavior.
Documented attack patterns abuse exactly the kind of access bazel_macos_launch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and XcodeBazelMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for bazel_macos_launch:
{
"version": "1",
"default": "deny",
"tools": {
"bazel_macos_launch": {
"limits": [
{
"counter": "bazel_macos_launch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}bazel_macos_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 previously built macOS application by its bundle path or target label. It is categorised as a Execute tool in the XcodeBazelMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the XcodeBazel MCP server in PolicyLayer and add a rule for bazel_macos_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 XcodeBazelMCP. Nothing to install.
bazel_macos_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 bazel_macos_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 bazel_macos_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.
bazel_macos_launch is provided by the XcodeBazel MCP server (xcodebazelmcp/xcodebazelmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from XcodeBazelMCP, 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.
117 XcodeBazelMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.