Navigate to a URL. Opens the browser if not already running. Only http: and https: URLs are accepted (plus the special about:blank). Other URL schemes (file:, chrome:, chrome-extension:, javascript:, data:, view-source:, about:*) are refused. IMPORTANT: After navigating, call browser_snapshot to ...
AI agents invoke browser_navigate to trigger actions in Apple Shortcuts. 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.
browser_navigate performs an external action that cannot be fully predicted or contained: it launches a browser process and navigates to a specified URL. While the tool restricts schemes to http/https (blocking file:, javascript:, etc.), the actual consequences of navigating to a URL—what scripts execute, what data is leaked, what prompts appear—depend on the destination and are not reversible (user interaction or…
From the tool's definition Tool description states it "Navigate to a URL. Opens the browser if not already running." — this triggers external operations (browser launch and navigation) whose effects depend on the URL argument provided.
Documented attack patterns abuse exactly the kind of access browser_navigate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Shortcuts, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_navigate:
{
"version": "1",
"default": "deny",
"tools": {
"browser_navigate": {
"limits": [
{
"counter": "browser_navigate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} browser_navigate 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.
Navigate to a URL. Opens the browser if not already running. Only http: and https: URLs are accepted (plus the special about:blank). Other URL schemes (file:, chrome:, chrome-extension:, javascript:, data:, view-source:, about:*) are refused. IMPORTANT: After navigating, call browser_snapshot to see the page content before interacting. It is categorised as a Execute tool in the Apple Shortcuts MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Apple Shortcuts MCP server in PolicyLayer and add a rule for browser_navigate: 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 Apple Shortcuts. Nothing to install.
browser_navigate 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 browser_navigate 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 browser_navigate. 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.
browser_navigate is provided by the Apple Shortcuts MCP server (@mindstone/mcp-server-apple-shortcuts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Shortcuts, 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.
423 Apple Shortcuts tools catalogued and risk-classified — across an index of 43,000+ MCP servers.