AI agents invoke safari_tabs 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 performs multiple browser tab operations including creating and closing tabs (destructive/write actions) and selecting tabs (execute). Since it spans multiple categories, the most severe applicable is Execute (browser actions). Closing tabs could result in loss of unsaved data. The tool triggers external browser operations whose effects depend on arguments passed to it.
From the tool's definition List, create, close, or select a browser tab
Attacks that exploit this kind of access
List, create, close, or select a browser tab. Use waitUntil with action=. 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_tabs: 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_tabs 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_tabs 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_tabs. 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_tabs 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 →