Switch to a different browser page (tab) (see browser_docs)
AI agents invoke browser_switch_page to trigger actions in Browser MCP Server. 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.
Switching browser tabs is a browser action that changes the active context for subsequent operations. It's not a pure read (it changes state), not write (no data creation/modification), but an Execute-level browser control action. Misuse could redirect agent attention to unintended pages, potentially enabling further exploitation through context switching.
From the tool's definition Switch to a different browser page (tab)
Attacks that exploit this kind of access
Switch to a different browser page (tab) (see browser_docs). It is categorised as a Execute tool in the Browser MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser MCP Server MCP server in PolicyLayer and add a rule for browser_switch_page: 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 Browser MCP Server. Nothing to install.
browser_switch_page 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_switch_page 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_switch_page. 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_switch_page is provided by the Browser MCP Server MCP server (madebytokens/browser-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 →