Select an Arc tab by explicit id. This changes visible Arc state.
AI agents invoke arc_select_tab to trigger actions in Arc Browser MCP. 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.
Selecting a tab triggers a browser UI action that changes the visible state of the Arc browser. This is not a pure read (it modifies what the user sees) nor a write to persistent data, but rather an execution of a browser action with side effects on the application state.
From the tool's definition 'Select an Arc tab by explicit id. This changes visible Arc state.'
Attacks that exploit this kind of access
Select an Arc tab by explicit id. This changes visible Arc state. It is categorised as a Execute tool in the Arc Browser MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Arc Browser MCP server in PolicyLayer and add a rule for arc_select_tab: 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 Arc Browser MCP. Nothing to install.
arc_select_tab 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 arc_select_tab 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 arc_select_tab. 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.
arc_select_tab is provided by the Arc Browser MCP server (jasoncronje/arc-browser-mcp). 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 →