Close a page
AI agents invoke close_page to trigger actions in MCP Playwright 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.
Closing a page is a browser action that triggers an external operation (destroying a browser page context). While it doesn't delete persistent data, it is an irreversible action within the session that could cause loss of unsaved state or disrupt ongoing automation workflows. It falls under Execute as it controls external browser behavior rather than reading or writing data.
From the tool's definition Close a page — terminates an active browser page/tab, which is an external browser operation with side effects
Attacks that exploit this kind of access
Close a page. It is categorised as a Execute tool in the MCP Playwright Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Playwright Server MCP server in PolicyLayer and add a rule for close_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 MCP Playwright Server. Nothing to install.
close_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 close_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 close_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.
close_page is provided by the MCP Playwright Server MCP server (mostafaraafat91/mcp-playwright-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 →