Close the specified browser instance
AI agents call browser_close_instance to permanently remove resources in Concurrent Browser MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a browser instance is an irreversible action that terminates the instance and destroys its state (open tabs, session data, in-memory context). Unlike navigating back or modifying content, this cannot be undone — the instance and all its associated state are gone. Severity is medium because it affects only a single browser instance, not persistent user data or external systems.
From the tool's definition Close the specified browser instance
Documented attack patterns abuse exactly the kind of access browser_close_instance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Concurrent Browser MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_close_instance:
{
"version": "1",
"default": "deny",
"hide": [
"browser_close_instance"
]
} browser_close_instance disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Close the specified browser instance. It is categorised as a Destructive tool in the Concurrent Browser MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Concurrent Browser MCP server in PolicyLayer and add a rule for browser_close_instance: 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 Concurrent Browser MCP. Nothing to install.
browser_close_instance is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the browser_close_instance 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_close_instance. 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_close_instance is provided by the Concurrent Browser MCP server (sailaoda/concurrent-browser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Concurrent Browser MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 Concurrent Browser MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.