Select a page as a context for future tool calls.
AI agents invoke select_page to trigger actions in Chrome Devtools. 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 page changes the execution context for all future browser automation actions. While it doesn't directly read or write data, it is a stateful operation that redirects subsequent Execute-category actions (click, evaluate_script, fill, etc.) to a different target. This makes it an execution-context manipulation tool with medium severity, as misuse could redirect agent actions to unintended pages.
From the tool's definition 'Select a page as a context for future tool calls' — switches the active browser page/tab that subsequent tool calls will operate on
Attacks that exploit this kind of access
Select a page as a context for future tool calls. It is categorised as a Execute tool in the Chrome Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for select_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 Chrome Devtools. Nothing to install.
select_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 select_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 select_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.
select_page is provided by the Chrome Devtools MCP server (nimbus21/chrome-devtools-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 →