AI agents invoke safari_url to trigger actions in MacWright. 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.
This tool triggers an external browser navigation action — it causes Safari to load an arbitrary URL, which is an operation with external side effects (network requests, page loads, potential execution of web content). It goes beyond merely reading data; it actively drives browser behavior. An AI agent could misuse it to navigate to malicious sites, trigger downloads, or interact with web services.
From the tool's definition Navigate Safari to a URL... Auto-opens Safari if not running
Attacks that exploit this kind of access
Navigate Safari to a URL or get the current URL. Much more reliable than clicking the address bar. Works without Accessibility permissions. Auto-opens Safari if not running. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MacWright MCP server in PolicyLayer and add a rule for safari_url: 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 MacWright. Nothing to install.
safari_url 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 safari_url 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 safari_url. 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.
safari_url is provided by the MacWright MCP server (ruchit-p/macwright). 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 →