Navigate to a URL in a web browser with automatic verification. Uses Cmd+L to focus address bar, types the URL, presses Return, and verifies navigation succeeded by checking the actual URL via AppleScript. Retries up to 3 times if navigation fails. Much more reliable than separate type+key commands.
AI agents invoke pilotgentic_navigate to trigger actions in PilotGentic. 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.
Navigation is an Execute category action because it runs external operations (HTTP requests, page loads, potential script execution) whose consequences depend on the agent's choice of URL. While not Destructive or Financial by itself, it can be weaponized to visit malicious sites, trigger unintended transactions, or interact with sensitive web applications.
From the tool's definition The tool navigates to URLs in a web browser, which triggers external operations (loading web pages, executing scripts on those pages, potentially triggering side effects across the internet).
Attacks that exploit this kind of access
Navigate to a URL in a web browser with automatic verification. Uses Cmd+L to focus address bar, types the URL, presses Return, and verifies navigation succeeded by checking the actual URL via AppleScript. Retries up to 3 times if navigation fails. Much more reliable than separate type+key commands. It is categorised as a Execute tool in the PilotGentic MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PilotGentic MCP server in PolicyLayer and add a rule for pilotgentic_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 PilotGentic. Nothing to install.
pilotgentic_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 pilotgentic_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 pilotgentic_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.
pilotgentic_navigate is provided by the PilotGentic MCP server (@pilotgentic/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →