AI agents invoke switch_tab to trigger actions in PageMap. 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 the active tab changes the browser's operational context, affecting all subsequent tool calls. This is a browser action that triggers external operation state changes — it's not a pure read, and its effects (redirecting agent actions to a different tab) can have cascading consequences depending on what operations follow.
From the tool's definition 'Switch the active tab. All subsequent tool calls operate on this tab.'
Attacks that exploit this kind of access
Switch the active tab. All subsequent tool calls operate on this tab. It is categorised as a Execute tool in the PageMap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PageMap MCP server in PolicyLayer and add a rule for switch_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 PageMap. Nothing to install.
switch_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 switch_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 switch_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.
switch_tab is provided by the PageMap MCP server (oci:docker.io/retio1001/pagemap:0.7.3). 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 →